Search

Your search keyword '"Timofte, R."' showing total 39 results
Start Over Author "Timofte, R."

Refine your results

more »

more »

more »
39 results on '"Timofte, R."'

1. NTIRE 2023 Quality Assessment of Video Enhancement Challenge

Author

Liu, X, Min, X, Sun, W, Zhang, Y, Zhang, K, Timofte, R, Zhai, G, Gao, Y, Cao, Y, Kou, T, Dong, Y, Jia, Z, Li, Y, Wu, W, Hu, S, Deng, S, Xiao, P, Chen, Y, Li, K, Zhao, K, Yuan, K, Sun, M, Cong, H, Wang, H, Fu, L, Zhang, R, Shi, H, Xu, Q, Xiao, L, Ma, Z, Agarla, M, Celona, L, Rota, C, Schettini, R, Huang, Z, Wang, X, Lei, L, Liu, H, Hong, W, Chuang, I, Lin, A, Guan, D, Chen, I, Lou, K, Huang, W, Tasi, Y, Kao, Y, Fan, H, Kong, F, Zhou, S, Lai, Y, Chen, S, Wang, W, Wu, H, Chen, C, Zhu, C, Guo, Z, Zhao, S, Yin, H, Meftah, H, Fezza, S, Hamidouche, W, Déforges, O, Shi, T, Mansouri, A, Motamednia, H, Bakhtiari, A, Aznaveh, A, Liu X., Min X., Sun W., Zhang Y., Zhang K., Timofte R., Zhai G., Gao Y., Cao Y., Kou T., Dong Y., Jia Z., Li Y., Wu W., Hu S., Deng S., Xiao P., Chen Y., Li K., Zhao K., Yuan K., Sun M., Cong H., Wang H., Fu L., Zhang R., Shi H., Xu Q., Xiao L., Ma Z., Agarla M., Celona L., Rota C., Schettini R., Huang Z., Wang X., Lei L., Liu H., Hong W., Chuang I., Lin A., Guan D., Chen I., Lou K., Huang W., Tasi Y., Kao Y., Fan H., Kong F., Zhou S., Lai Y., Chen S., Wang W., Wu H., Chen C., Zhu C., Guo Z., Zhao S., Yin H., Meftah H. B., Fezza S. A., Hamidouche W., Déforges O., Shi T., Mansouri A., Motamednia H., Bakhtiari A. H., Aznaveh A. M., Liu, X, Min, X, Sun, W, Zhang, Y, Zhang, K, Timofte, R, Zhai, G, Gao, Y, Cao, Y, Kou, T, Dong, Y, Jia, Z, Li, Y, Wu, W, Hu, S, Deng, S, Xiao, P, Chen, Y, Li, K, Zhao, K, Yuan, K, Sun, M, Cong, H, Wang, H, Fu, L, Zhang, R, Shi, H, Xu, Q, Xiao, L, Ma, Z, Agarla, M, Celona, L, Rota, C, Schettini, R, Huang, Z, Wang, X, Lei, L, Liu, H, Hong, W, Chuang, I, Lin, A, Guan, D, Chen, I, Lou, K, Huang, W, Tasi, Y, Kao, Y, Fan, H, Kong, F, Zhou, S, Lai, Y, Chen, S, Wang, W, Wu, H, Chen, C, Zhu, C, Guo, Z, Zhao, S, Yin, H, Meftah, H, Fezza, S, Hamidouche, W, Déforges, O, Shi, T, Mansouri, A, Motamednia, H, Bakhtiari, A, Aznaveh, A, Liu X., Min X., Sun W., Zhang Y., Zhang K., Timofte R., Zhai G., Gao Y., Cao Y., Kou T., Dong Y., Jia Z., Li Y., Wu W., Hu S., Deng S., Xiao P., Chen Y., Li K., Zhao K., Yuan K., Sun M., Cong H., Wang H., Fu L., Zhang R., Shi H., Xu Q., Xiao L., Ma Z., Agarla M., Celona L., Rota C., Schettini R., Huang Z., Wang X., Lei L., Liu H., Hong W., Chuang I., Lin A., Guan D., Chen I., Lou K., Huang W., Tasi Y., Kao Y., Fan H., Kong F., Zhou S., Lai Y., Chen S., Wang W., Wu H., Chen C., Zhu C., Guo Z., Zhao S., Yin H., Meftah H. B., Fezza S. A., Hamidouche W., Déforges O., Shi T., Mansouri A., Motamednia H., Bakhtiari A. H., and Aznaveh A. M.

Abstract

This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2023. This challenge is to address a major challenge in the field of video processing, namely, video quality assessment (VQA) for enhanced videos. The challenge uses the VQA Dataset for Perceptual Video Enhancement (VDPVE), which has a total of 1211 enhanced videos, including 600 videos with color, brightness, and contrast enhancements, 310 videos with deblurring, and 301 deshaked videos. The challenge has a total of 167 registered participants. 61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions. A total of 176 submissions were submitted by 37 participating teams during the final testing phase. Finally, 19 participating teams submitted their models and fact sheets, and detailed the methods they used. Some methods have achieved better results than baseline methods, and the winning methods have demonstrated superior prediction performance.

Published
2023

2. NTIRE 2023 Challenge on Night Photography Rendering

Author

Shutova, A, Ershov, E, Perevozchikov, G, Ermakov, I, Banic, N, Timofte, R, Collins, R, Efimova, M, Terekhin, A, Zini, S, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Lei, C, Wang, T, Wang, S, Liu, S, Feng, C, Shao, G, Wang, H, Wang, X, Lei, L, Xu, L, Zhang, C, Wang, Y, Guo, J, Sun, Y, Liu, T, Hao, D, Kinli, F, Ozcan, B, Kirac, F, Chung, H, Lee, N, Kwak, S, Conde, M, Elezabi, O, Seizinger, T, Vasluianu, F, Hsieh, C, Chen, W, Yang, H, Huang, Z, Chang, H, Chen, I, Chen, Y, Chiang, Y, Kuo, S, Shutova A., Ershov E., Perevozchikov G., Ermakov I., Banic N., Timofte R., Collins R., Efimova M., Terekhin A., Zini S., Rota C., Buzzelli M., Bianco S., Schettini R., Lei C., Wang T., Wang S., Liu S., Feng C., Shao G., Wang H., Wang X., Lei L., Xu L., Zhang C., Wang Y., Guo J., Sun Y., Liu T., Hao D., Kinli F., Ozcan B., Kirac F., Chung H., Lee N., Kwak S. K., Conde M., Elezabi O., Seizinger T., Vasluianu F., Hsieh C. -H., Chen W. -T., Yang H. -H., Huang Z. -K., Chang H. -E., Chen I. -H., Chen Y. -C., Chiang Y. -C., Kuo S. -Y., Shutova, A, Ershov, E, Perevozchikov, G, Ermakov, I, Banic, N, Timofte, R, Collins, R, Efimova, M, Terekhin, A, Zini, S, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Lei, C, Wang, T, Wang, S, Liu, S, Feng, C, Shao, G, Wang, H, Wang, X, Lei, L, Xu, L, Zhang, C, Wang, Y, Guo, J, Sun, Y, Liu, T, Hao, D, Kinli, F, Ozcan, B, Kirac, F, Chung, H, Lee, N, Kwak, S, Conde, M, Elezabi, O, Seizinger, T, Vasluianu, F, Hsieh, C, Chen, W, Yang, H, Huang, Z, Chang, H, Chen, I, Chen, Y, Chiang, Y, Kuo, S, Shutova A., Ershov E., Perevozchikov G., Ermakov I., Banic N., Timofte R., Collins R., Efimova M., Terekhin A., Zini S., Rota C., Buzzelli M., Bianco S., Schettini R., Lei C., Wang T., Wang S., Liu S., Feng C., Shao G., Wang H., Wang X., Lei L., Xu L., Zhang C., Wang Y., Guo J., Sun Y., Liu T., Hao D., Kinli F., Ozcan B., Kirac F., Chung H., Lee N., Kwak S. K., Conde M., Elezabi O., Seizinger T., Vasluianu F., Hsieh C. -H., Chen W. -T., Yang H. -H., Huang Z. -K., Chang H. -E., Chen I. -H., Chen Y. -C., Chiang Y. -C., and Kuo S. -Y.

Abstract

This paper presents a review of the NTIRE 2023 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions conditions, and thereby produce a photo-quality output images in the standard RGB (sRGB) space. Unlike the previous year's competition, participants were not provided with a large training dataset for the target sensor. Instead, this time they were given images of a color checker illuminated by a known light source. To evaluate the results, a sufficient number of viewers were asked to assess the visual quality of the proposed solutions, considering the subjective nature of the task. The highest ranking solutions were further ranked by Richard Collins, a renowned photographer. The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering. More results can be found at https://nightimaging.org

Published
2023

3. AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results

Author

Karlinsky, L, Michaeli, T, Nishino, K, Yang, R, Timofte, R, Li, X, Zhang, Q, Zhang, L, Liu, F, He, D, Li, F, Zheng, H, Yuan, W, Ostyakov, P, Vyal, D, Zhussip, M, Zou, X, Yan, Y, Li, L, Tang, J, Chen, M, Zhao, S, Zhu, Y, Qin, X, Li, C, Leng, C, Cheng, J, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Zhang, D, Huang, F, Liu, S, Wang, X, Jin, Z, Li, B, Li, M, Liu, D, Zou, W, Dong, P, Ye, T, Zhang, Y, Tan, M, Niu, X, Ayazoglu, M, Conde, M, Choi, U, Jia, Z, Xu, T, Ye, M, Luo, D, Pan, X, Peng, L, Yang R., Timofte R., Li X., Zhang Q., Zhang L., Liu F., He D., Li F., Zheng H., Yuan W., Ostyakov P., Vyal D., Zhussip M., Zou X., Yan Y., Li L., Tang J., Chen M., Zhao S., Zhu Y., Qin X., Li C., Leng C., Cheng J., Rota C., Buzzelli M., Bianco S., Schettini R., Zhang D., Huang F., Liu S., Wang X., Jin Z., Li B., Li M., Liu D., Zou W., Dong P., Ye T., Zhang Y., Tan M., Niu X., Ayazoglu M., Conde M., Choi U. J., Jia Z., Xu T., Ye M., Luo D., Pan X., Peng L., Karlinsky, L, Michaeli, T, Nishino, K, Yang, R, Timofte, R, Li, X, Zhang, Q, Zhang, L, Liu, F, He, D, Li, F, Zheng, H, Yuan, W, Ostyakov, P, Vyal, D, Zhussip, M, Zou, X, Yan, Y, Li, L, Tang, J, Chen, M, Zhao, S, Zhu, Y, Qin, X, Li, C, Leng, C, Cheng, J, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Zhang, D, Huang, F, Liu, S, Wang, X, Jin, Z, Li, B, Li, M, Liu, D, Zou, W, Dong, P, Ye, T, Zhang, Y, Tan, M, Niu, X, Ayazoglu, M, Conde, M, Choi, U, Jia, Z, Xu, T, Ye, M, Luo, D, Pan, X, Peng, L, Yang R., Timofte R., Li X., Zhang Q., Zhang L., Liu F., He D., Li F., Zheng H., Yuan W., Ostyakov P., Vyal D., Zhussip M., Zou X., Yan Y., Li L., Tang J., Chen M., Zhao S., Zhu Y., Qin X., Li C., Leng C., Cheng J., Rota C., Buzzelli M., Bianco S., Schettini R., Zhang D., Huang F., Liu S., Wang X., Jin Z., Li B., Li M., Liu D., Zou W., Dong P., Ye T., Zhang Y., Tan M., Niu X., Ayazoglu M., Conde M., Choi U. J., Jia Z., Xu T., Ye M., Luo D., Pan X., and Peng L.

Abstract

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track 2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

Published
2023

5. NTIRE 2022 Challenge on Night Photography Rendering

Author

Ershov, E, Savchik, A, Shepelev, D, Banic, N, Brown, M, Timofte, R, Koscevic, K, Freeman, M, Tesalin, V, Bocharov, D, Semenkov, I, Subasic, M, Loncaric, S, Terekhin, A, Liu, S, Feng, C, Wang, H, Zhu, R, Li, Y, Lei, L, Li, Z, Yi, S, Han, L, Wu, R, Jin, X, Guo, C, Kinli, F, Mentes, S, Ozcan, B, Kirac, F, Zini, S, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Li, W, Ma, Y, Wang, T, Xu, R, Song, F, Chen, W, Yang, H, Huang, Z, Chang, H, Kuo, S, Liang, Z, Zhou, S, Feng, R, Li, C, Chen, X, Song, B, Zhang, S, Liu, L, Wang, Z, Ryu, D, Bae, H, Kwon, T, Desai, C, Akalwadi, N, Joshi, A, Mandi, C, Malagi, S, Uppin, A, Sudheer Reddy, S, Ashok Tabib, R, Patil, U, Mudenagudi, U, Ershov, Egor, Savchik, Alex, Shepelev, Denis, Banic, Nikola, Brown, Michael S., Timofte, Radu, Koscevic, Karlo, Freeman, Michael, Tesalin, Vasily, Bocharov, Dmitry, Semenkov, Illya, Subasic, Marko, Loncaric, Sven, Terekhin, Arseniy, Liu, Shuai, Feng, Chaoyu, Wang, Hao, Zhu, Ran, Li, Yongqiang, Lei, Lei, Li, Zhihao, Yi, Si, Han, Ling-Hao, Wu, Ruiqi, Jin, Xin, Guo, Chunle, Kinli, Furkan, Mentes, Sami, Ozcan, Baris, Kirac, Furkan, Zini, Simone, Rota, Claudio, Buzzelli, Marco, Bianco, Simone, Schettini, Raimondo, Li, Wei, Ma, Yipeng, Wang, Tao, Xu, Ruikang, Song, Fenglong, Chen, Wei-Ting, Yang, Hao-Hsiang, Huang, Zhi-Kai, Chang, Hua-En, Kuo, Sy-Yen, Liang, Zhexin, Zhou, Shangchen, Feng, Ruicheng, Li, Chongyi, Chen, Xiangyu, Song, Binbin, Zhang, Shile, Liu, Lin, Wang, Zhendong, Ryu, Dohoon, Bae, Hyokyoung, Kwon, Taesung, Desai, Chaitra, Akalwadi, Nikhil, Joshi, Amogh, Mandi, Chinmayee, Malagi, Sampada, Uppin, Akash, Sudheer Reddy, Sai, Ashok Tabib, Ramesh, Patil, Ujwala, Mudenagudi, Uma, Ershov, E, Savchik, A, Shepelev, D, Banic, N, Brown, M, Timofte, R, Koscevic, K, Freeman, M, Tesalin, V, Bocharov, D, Semenkov, I, Subasic, M, Loncaric, S, Terekhin, A, Liu, S, Feng, C, Wang, H, Zhu, R, Li, Y, Lei, L, Li, Z, Yi, S, Han, L, Wu, R, Jin, X, Guo, C, Kinli, F, Mentes, S, Ozcan, B, Kirac, F, Zini, S, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Li, W, Ma, Y, Wang, T, Xu, R, Song, F, Chen, W, Yang, H, Huang, Z, Chang, H, Kuo, S, Liang, Z, Zhou, S, Feng, R, Li, C, Chen, X, Song, B, Zhang, S, Liu, L, Wang, Z, Ryu, D, Bae, H, Kwon, T, Desai, C, Akalwadi, N, Joshi, A, Mandi, C, Malagi, S, Uppin, A, Sudheer Reddy, S, Ashok Tabib, R, Patil, U, Mudenagudi, U, Ershov, Egor, Savchik, Alex, Shepelev, Denis, Banic, Nikola, Brown, Michael S., Timofte, Radu, Koscevic, Karlo, Freeman, Michael, Tesalin, Vasily, Bocharov, Dmitry, Semenkov, Illya, Subasic, Marko, Loncaric, Sven, Terekhin, Arseniy, Liu, Shuai, Feng, Chaoyu, Wang, Hao, Zhu, Ran, Li, Yongqiang, Lei, Lei, Li, Zhihao, Yi, Si, Han, Ling-Hao, Wu, Ruiqi, Jin, Xin, Guo, Chunle, Kinli, Furkan, Mentes, Sami, Ozcan, Baris, Kirac, Furkan, Zini, Simone, Rota, Claudio, Buzzelli, Marco, Bianco, Simone, Schettini, Raimondo, Li, Wei, Ma, Yipeng, Wang, Tao, Xu, Ruikang, Song, Fenglong, Chen, Wei-Ting, Yang, Hao-Hsiang, Huang, Zhi-Kai, Chang, Hua-En, Kuo, Sy-Yen, Liang, Zhexin, Zhou, Shangchen, Feng, Ruicheng, Li, Chongyi, Chen, Xiangyu, Song, Binbin, Zhang, Shile, Liu, Lin, Wang, Zhendong, Ryu, Dohoon, Bae, Hyokyoung, Kwon, Taesung, Desai, Chaitra, Akalwadi, Nikhil, Joshi, Amogh, Mandi, Chinmayee, Malagi, Sampada, Uppin, Akash, Sudheer Reddy, Sai, Ashok Tabib, Ramesh, Patil, Ujwala, and Mudenagudi, Uma

Abstract

This paper reviews the NTIRE 2022 challenge on night photography rendering. The challenge solicited solutions that processed RAW camera images captured in night scenes to produce a photo-finished output image encoded in the standard RGB (sRGB) space. Given the subjective nature of this task, the proposed solutions were evaluated based on the mean opinions of viewers asked to judge the visual appearance of the results. Michael Freeman, a world-renowned photographer, further ranked the solutions with the highest mean opinion scores. A total of 13 teams competed in the final phase of the challenge. The proposed methods provided by the participating teams represent state-of-the-art performance in nighttime photography. Results from the various teams can be found here: https://nightimaging.org

Published
2022

6. NTIRE 2022 Spectral Recovery Challenge and Data Set

Author

Arad, B, Timofte, R, Yahel, R, Morag, N, Bernat, A, Cai, Y, Lin, J, Lin, Z, Wang, H, Zhang, Y, Pfister, H, Van Gool, L, Liu, S, Li, Y, Feng, C, Lei, L, Li, J, Du, S, Wu, C, Leng, Y, Song, R, Zhang, M, Song, C, Zhao, S, Lang, Z, Wei, W, Zhang, L, Dian, R, Shan, T, Guo, A, Liu, J, Agarla, M, Bianco, S, Buzzelli, M, Celona, L, Schettini, R, He, J, Xiao, Y, Xiao, J, Yuan, Q, Kwon, T, Ryu, D, Bae, H, Yang, H, Chang, H, Huang, Z, Chen, W, Kuo, S, Chen, J, Li, H, Sabarinathan, S, Uma, K, Bama, B, Roomi, S, Arad, Boaz, Timofte, Radu, Yahel, Rony, Morag, Nimrod, Bernat, Amir, Cai, Yuanhao, Lin, Jing, Lin, Zudi, Wang, Haoqian, Zhang, Yulun, Pfister, Hanspeter, Van Gool, Luc, Liu, Shuai, Li, Yongqiang, Feng, Chaoyu, Lei, Lei, Li, Jiaojiao, Du, Songcheng, Wu, Chaoxiong, Leng, Yihong, Song, Rui, Zhang, Mingwei, Song, Chongxing, Zhao, Shuyi, Lang, Zhiqiang, Wei, Wei, Zhang, Lei, Dian, Renwei, Shan, Tianci, Guo, Anjing, Feng, Chengguo, Liu, Jinyang, Agarla, Mirko, Bianco, Simone, Buzzelli, Marco, Celona, Luigi, Schettini, Raimondo, He, Jiang, Xiao, Yi, Xiao, Jiajun, Yuan, Qiangqiang, Li, Jie, Zhang, Liangpei, Kwon, Taesung, Ryu, Dohoon, Bae, Hyokyoung, Yang, Hao-Hsiang, Chang, Hua-En, Huang, Zhi-Kai, Chen, Wei-Ting, Kuo, Sy-Yen, Chen, Junyu, Li, Haiwei, Liu, Song, Sabarinathan, Sabarinathan, Bama, B Sathya, Roomi, S. Mohamed Mansoor, Arad, B, Timofte, R, Yahel, R, Morag, N, Bernat, A, Cai, Y, Lin, J, Lin, Z, Wang, H, Zhang, Y, Pfister, H, Van Gool, L, Liu, S, Li, Y, Feng, C, Lei, L, Li, J, Du, S, Wu, C, Leng, Y, Song, R, Zhang, M, Song, C, Zhao, S, Lang, Z, Wei, W, Zhang, L, Dian, R, Shan, T, Guo, A, Liu, J, Agarla, M, Bianco, S, Buzzelli, M, Celona, L, Schettini, R, He, J, Xiao, Y, Xiao, J, Yuan, Q, Kwon, T, Ryu, D, Bae, H, Yang, H, Chang, H, Huang, Z, Chen, W, Kuo, S, Chen, J, Li, H, Sabarinathan, S, Uma, K, Bama, B, Roomi, S, Arad, Boaz, Timofte, Radu, Yahel, Rony, Morag, Nimrod, Bernat, Amir, Cai, Yuanhao, Lin, Jing, Lin, Zudi, Wang, Haoqian, Zhang, Yulun, Pfister, Hanspeter, Van Gool, Luc, Liu, Shuai, Li, Yongqiang, Feng, Chaoyu, Lei, Lei, Li, Jiaojiao, Du, Songcheng, Wu, Chaoxiong, Leng, Yihong, Song, Rui, Zhang, Mingwei, Song, Chongxing, Zhao, Shuyi, Lang, Zhiqiang, Wei, Wei, Zhang, Lei, Dian, Renwei, Shan, Tianci, Guo, Anjing, Feng, Chengguo, Liu, Jinyang, Agarla, Mirko, Bianco, Simone, Buzzelli, Marco, Celona, Luigi, Schettini, Raimondo, He, Jiang, Xiao, Yi, Xiao, Jiajun, Yuan, Qiangqiang, Li, Jie, Zhang, Liangpei, Kwon, Taesung, Ryu, Dohoon, Bae, Hyokyoung, Yang, Hao-Hsiang, Chang, Hua-En, Huang, Zhi-Kai, Chen, Wei-Ting, Kuo, Sy-Yen, Chen, Junyu, Li, Haiwei, Liu, Song, Sabarinathan, Sabarinathan, Bama, B Sathya, and Roomi, S. Mohamed Mansoor

Abstract

This paper reviews the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. This challenge presents the "ARAD_1K" data set: a new, larger-than-ever natural hyperspectral image data set containing 1,000 images. Challenge participants were required to recover hyper-spectral information from synthetically generated JPEG-compressed RGB images simulating capture by a known calibrated camera, operating under partially known parameters, in a setting which includes acquisition noise. The challenge was attended by 241 teams, with 60 teams com-peting in the final testing phase, 12 of which provided de-tailed descriptions of their methodology which are included in this report. The performance of these submissions is re-viewed and provided here as a gauge for the current state-of-the-art in spectral reconstruction from natural RGB images.

Published
2022

7. NTIRE 2019 challenge on image enhancement: Methods and results

Author

Ignatov, A, Timofte, R, Qu, X, Zhou, X, Liu, T, Wan, P, Zamir, S, Arora, A, Khan, S, Khan, F, Shao, L, Park, D, Chun, S, Michelini, P, Liu, H, Zhu, D, Zhong, Z, Liu, X, Jiang, J, Zhao, D, Haris, M, Akita, K, Yoshida, T, Shakhnarovich, G, Ukita, N, Liu, J, Jung, C, Schettini, R, Bianco, S, Cusano, C, Piccoli, F, Liu, P, Zhang, K, Zhang, H, Zuo, W, Bow, N, Wong, L, See, J, Qin, J, Huang, L, Shi, Y, Wei, P, Wen, W, Lin, L, Hui, Z, Wang, X, Gao, X, Kumari, K, Anand, V, Khened, M, Krishnamurthi, G, Ignatov A., Timofte R., Qu X., Zhou X., Liu T., Wan P., Zamir S. W., Arora A., Khan S., Khan F. S., Shao L., Park D., Chun S. Y., Michelini P. N., Liu H., Zhu D., Zhong Z., Liu X., Jiang J., Zhao D., Haris M., Akita K., Yoshida T., Shakhnarovich G., Ukita N., Liu J., Jung C., Schettini R., Bianco S., Cusano C., Piccoli F., Liu P., Zhang K., Zhang H., Zuo W., Bow N. C. N., Wong L. -K., See J., Qin J., Huang L., Shi Y., Wei P., Wen W., Lin L., Hui Z., Wang X., Gao X., Kumari K., Anand V. K., Khened M., Krishnamurthi G., Ignatov, A, Timofte, R, Qu, X, Zhou, X, Liu, T, Wan, P, Zamir, S, Arora, A, Khan, S, Khan, F, Shao, L, Park, D, Chun, S, Michelini, P, Liu, H, Zhu, D, Zhong, Z, Liu, X, Jiang, J, Zhao, D, Haris, M, Akita, K, Yoshida, T, Shakhnarovich, G, Ukita, N, Liu, J, Jung, C, Schettini, R, Bianco, S, Cusano, C, Piccoli, F, Liu, P, Zhang, K, Zhang, H, Zuo, W, Bow, N, Wong, L, See, J, Qin, J, Huang, L, Shi, Y, Wei, P, Wen, W, Lin, L, Hui, Z, Wang, X, Gao, X, Kumari, K, Anand, V, Khened, M, Krishnamurthi, G, Ignatov A., Timofte R., Qu X., Zhou X., Liu T., Wan P., Zamir S. W., Arora A., Khan S., Khan F. S., Shao L., Park D., Chun S. Y., Michelini P. N., Liu H., Zhu D., Zhong Z., Liu X., Jiang J., Zhao D., Haris M., Akita K., Yoshida T., Shakhnarovich G., Ukita N., Liu J., Jung C., Schettini R., Bianco S., Cusano C., Piccoli F., Liu P., Zhang K., Zhang H., Zuo W., Bow N. C. N., Wong L. -K., See J., Qin J., Huang L., Shi Y., Wei P., Wen W., Lin L., Hui Z., Wang X., Gao X., Kumari K., Anand V. K., Khened M., and Krishnamurthi G.

Abstract

This paper reviews the first NTIRE challenge on perceptual image enhancement with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with Canon 70D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image denoising, image resolution and sharpness enhancement, image color/contrast/exposure adjustment, etc. The target metric used in this challenge combined PSNR and SSIM scores with solutions' perceptual results measured in the user study. The proposed solutions significantly improved baseline results, defining the state-of-the-art for practical image enhancement.

Published
2019

8. NTIRE 2019 challenge on real image denoising: Methods and results

Author

Abdelhamed, A, Timofte, R, Brown, M, Yu, S, Park, B, Jeong, J, Jung, S, Kim, D, Chung, J, Liu, J, Wang, Y, Wu, C, Xu, Q, Wang, C, Cai, S, Ding, Y, Fan, H, Wang, J, Zhang, K, Zuo, W, Zhussip, M, Park, D, Soltanayev, S, Chun, S, Xiong, Z, Chen, C, Haris, M, Akita, K, Yoshida, T, Shakhnarovich, G, Ukita, N, Zamir, S, Arora, A, Khan, S, Khan, F, Shao, L, Ko, S, Lim, D, Kim, S, Ji, S, Lee, S, Tang, W, Fan, Y, Zhou, Y, Liu, D, Huang, T, Meng, D, Zhang, L, Yong, H, Zhao, Y, Tang, P, Lu, Y, Schettini, R, Bianco, S, Zini, S, Li, C, Cao, Z, Abdelhamed A., Timofte R., Brown M. S., Yu S., Park B., Jeong J., Jung S. -W., Kim D. -W., Chung J. -R., Liu J., Wang Y., Wu C. -H., Xu Q., Wang C., Cai S., DIng Y., Fan H., Wang J., Zhang K., Zuo W., Zhussip M., Park D. W., Soltanayev S., Chun S. Y., Xiong Z., Chen C., Haris M., Akita K., Yoshida T., Shakhnarovich G., Ukita N., Zamir S. W., Arora A., Khan S., Khan F. S., Shao L., Ko S. -J., Lim D. -P., Kim S. -W., Ji S. -W., Lee S. -W., Tang W., Fan Y., Zhou Y., Liu D., Huang T. S., Meng D., Zhang L., Yong H., Zhao Y., Tang P., Lu Y., Schettini R., Bianco S., Zini S., Li C., Cao Z., Abdelhamed, A, Timofte, R, Brown, M, Yu, S, Park, B, Jeong, J, Jung, S, Kim, D, Chung, J, Liu, J, Wang, Y, Wu, C, Xu, Q, Wang, C, Cai, S, Ding, Y, Fan, H, Wang, J, Zhang, K, Zuo, W, Zhussip, M, Park, D, Soltanayev, S, Chun, S, Xiong, Z, Chen, C, Haris, M, Akita, K, Yoshida, T, Shakhnarovich, G, Ukita, N, Zamir, S, Arora, A, Khan, S, Khan, F, Shao, L, Ko, S, Lim, D, Kim, S, Ji, S, Lee, S, Tang, W, Fan, Y, Zhou, Y, Liu, D, Huang, T, Meng, D, Zhang, L, Yong, H, Zhao, Y, Tang, P, Lu, Y, Schettini, R, Bianco, S, Zini, S, Li, C, Cao, Z, Abdelhamed A., Timofte R., Brown M. S., Yu S., Park B., Jeong J., Jung S. -W., Kim D. -W., Chung J. -R., Liu J., Wang Y., Wu C. -H., Xu Q., Wang C., Cai S., DIng Y., Fan H., Wang J., Zhang K., Zuo W., Zhussip M., Park D. W., Soltanayev S., Chun S. Y., Xiong Z., Chen C., Haris M., Akita K., Yoshida T., Shakhnarovich G., Ukita N., Zamir S. W., Arora A., Khan S., Khan F. S., Shao L., Ko S. -J., Lim D. -P., Kim S. -W., Ji S. -W., Lee S. -W., Tang W., Fan Y., Zhou Y., Liu D., Huang T. S., Meng D., Zhang L., Yong H., Zhao Y., Tang P., Lu Y., Schettini R., Bianco S., Zini S., Li C., and Cao Z.

Abstract

This paper reviews the NTIRE 2019 challenge on real image denoising with focus on the proposed methods and their results. The challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern raw-RGB and (2) the standard RGB (sRGB) color spaces. The tracks had 216 and 220 registered participants, respectively. A total of 15 teams, proposing 17 methods, competed in the final phase of the challenge. The proposed methods by the 15 teams represent the current state-of-the-art performance in image denoising targeting real noisy images.

Published
2019

9. NTIRE 2019 image dehazing challenge report

Author

Ancuti, C, Timofte, R, Van Gool, L, Zhang, L, Yang, M, Guo, T, Li, X, Cherukuri, V, Monga, V, Jiang, H, Yang, S, Liu, Y, Qu, X, Wan, P, Park, D, Chun, S, Hong, M, Huang, J, Chen, Y, Chen, S, Wang, B, Michelini, P, Liu, H, Zhu, D, Liu, J, Santra, S, Mondal, R, Chanda, B, Morales, P, Klinghoffer, T, Quan, L, Kim, Y, Liang, X, Li, R, Pan, J, Tang, J, Purohit, K, Suin, M, Rajagopalan, A, Schettini, R, Bianco, S, Piccoli, F, Cusano, C, Celona, L, Hwang, S, Ma, Y, Byun, H, Murala, S, Dudhane, A, Aulakh, H, Zheng, T, Zhang, T, Qin, W, Zhou, R, Wang, S, Tarel, J, Wang, C, Wu, J, Ancuti C. O., Ancuti C., Timofte R., Van Gool L., Zhang L., Yang M. -H., Guo T., Li X., Cherukuri V., Monga V., Jiang H., Yang S., Liu Y., Qu X., Wan P., Park D., Chun S. Y., Hong M., Huang J., Chen Y., Chen S., Wang B., Michelini P. N., Liu H., Zhu D., Liu J., Santra S., Mondal R., Chanda B., Morales P., Klinghoffer T., Quan L. M., Kim Y. -G., Liang X., Li R., Pan J., Tang J., Purohit K., Suin M., Rajagopalan A. N., Schettini R., Bianco S., Piccoli F., Cusano C., Celona L., Hwang S., Ma Y. S., Byun H., Murala S., Dudhane A., Aulakh H., Zheng T., Zhang T., Qin W., Zhou R., Wang S., Tarel J. -P., Wang C., Wu J., Ancuti, C, Timofte, R, Van Gool, L, Zhang, L, Yang, M, Guo, T, Li, X, Cherukuri, V, Monga, V, Jiang, H, Yang, S, Liu, Y, Qu, X, Wan, P, Park, D, Chun, S, Hong, M, Huang, J, Chen, Y, Chen, S, Wang, B, Michelini, P, Liu, H, Zhu, D, Liu, J, Santra, S, Mondal, R, Chanda, B, Morales, P, Klinghoffer, T, Quan, L, Kim, Y, Liang, X, Li, R, Pan, J, Tang, J, Purohit, K, Suin, M, Rajagopalan, A, Schettini, R, Bianco, S, Piccoli, F, Cusano, C, Celona, L, Hwang, S, Ma, Y, Byun, H, Murala, S, Dudhane, A, Aulakh, H, Zheng, T, Zhang, T, Qin, W, Zhou, R, Wang, S, Tarel, J, Wang, C, Wu, J, Ancuti C. O., Ancuti C., Timofte R., Van Gool L., Zhang L., Yang M. -H., Guo T., Li X., Cherukuri V., Monga V., Jiang H., Yang S., Liu Y., Qu X., Wan P., Park D., Chun S. Y., Hong M., Huang J., Chen Y., Chen S., Wang B., Michelini P. N., Liu H., Zhu D., Liu J., Santra S., Mondal R., Chanda B., Morales P., Klinghoffer T., Quan L. M., Kim Y. -G., Liang X., Li R., Pan J., Tang J., Purohit K., Suin M., Rajagopalan A. N., Schettini R., Bianco S., Piccoli F., Cusano C., Celona L., Hwang S., Ma Y. S., Byun H., Murala S., Dudhane A., Aulakh H., Zheng T., Zhang T., Qin W., Zhou R., Wang S., Tarel J. -P., Wang C., and Wu J.

Abstract

This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The training data consists from 55 hazy images (with dense haze generated in an indoor or outdoor environment) and their corresponding ground truth (haze-free) images of the same scene. The dense haze has been produced using a professional haze/fog generator that imitates the real conditions of haze scenes. The evaluation consists from the comparison of the dehazed images with the ground truth images. The dehazing process was learnable through provided pairs of haze-free and hazy train images. There were ~ 270 registered participants and 23 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.

Published
2019

10. The Eighth Visual Object Tracking VOT2020 Challenge Results

Author

Kristan, M., Leonardis, A., Matas, J., Felsberg, Michael, Pflugfelder, R., Kämäräinen, J.-K., Danelljan, M., Zajc, L.C., Lukežic, A., Drbohlav, O., He, Linbo, Zhang, Yushan, Yan, S., Yang, J., Fernández, G., Hauptmann, A., Memarmoghadam, A., García-Martín, Á., Robinson, Andreas, Varfolomieiev, A., Gebrehiwot, A.H., Uzun, B., Yan, B., Li, B., Qian, C., Tsai, C.-Y., Micheloni, C., Wang, D., Wang, F., Xie, F., Järemo-Lawin, Felix, Gustafsson, F., Foresti, G.L., Bhat, G., Chen, G., Ling, H., Zhang, H., Cevikalp, H., Zhao, H., Bai, H., Kuchibhotla, H.C., Saribas, H., Fan, H., Ghanei-Yakhdan, H., Li, H., Peng, H., Lu, H., Khaghani, J., Bescos, J., Li, J., Fu, J., Yu, J., Xu, J., Kittler, J., Yin, J., Lee, J., Yu, K., Liu, K., Yang, K., Dai, K., Cheng, L., Zhang, L., Wang, L., Van, Gool L., Bertinetto, L., Dunnhofer, M., Cheng, M., Dasari, M.M., Wang, N., Zhang, P., Torr, P.H.S., Wang, Q., Timofte, R., Gorthi, R.K.S., Choi, S., Marvasti-Zadeh, S.M., Zhao, S., Kasaei, S., Qiu, S., Chen, S., Schön, T.B., Xu, T., Lu, W., Hu, W., Zhou, W., Qiu, X., Ke, X., Wu, X.-J., Zhang, X., Yang, X., Zhu, X., Jiang, Y., Wang, Y., Chen, Y., Ye, Y., Li, Y., Yao, Y., Lee, Y., Gu, Y., Wang, Z., Tang, Z., Feng, Z.-H., Mai, Z., Zhang, Z., Wu, Z., Ma, Z., Kristan, M., Leonardis, A., Matas, J., Felsberg, Michael, Pflugfelder, R., Kämäräinen, J.-K., Danelljan, M., Zajc, L.C., Lukežic, A., Drbohlav, O., He, Linbo, Zhang, Yushan, Yan, S., Yang, J., Fernández, G., Hauptmann, A., Memarmoghadam, A., García-Martín, Á., Robinson, Andreas, Varfolomieiev, A., Gebrehiwot, A.H., Uzun, B., Yan, B., Li, B., Qian, C., Tsai, C.-Y., Micheloni, C., Wang, D., Wang, F., Xie, F., Järemo-Lawin, Felix, Gustafsson, F., Foresti, G.L., Bhat, G., Chen, G., Ling, H., Zhang, H., Cevikalp, H., Zhao, H., Bai, H., Kuchibhotla, H.C., Saribas, H., Fan, H., Ghanei-Yakhdan, H., Li, H., Peng, H., Lu, H., Khaghani, J., Bescos, J., Li, J., Fu, J., Yu, J., Xu, J., Kittler, J., Yin, J., Lee, J., Yu, K., Liu, K., Yang, K., Dai, K., Cheng, L., Zhang, L., Wang, L., Van, Gool L., Bertinetto, L., Dunnhofer, M., Cheng, M., Dasari, M.M., Wang, N., Zhang, P., Torr, P.H.S., Wang, Q., Timofte, R., Gorthi, R.K.S., Choi, S., Marvasti-Zadeh, S.M., Zhao, S., Kasaei, S., Qiu, S., Chen, S., Schön, T.B., Xu, T., Lu, W., Hu, W., Zhou, W., Qiu, X., Ke, X., Wu, X.-J., Zhang, X., Yang, X., Zhu, X., Jiang, Y., Wang, Y., Chen, Y., Ye, Y., Li, Y., Yao, Y., Lee, Y., Gu, Y., Wang, Z., Tang, Z., Feng, Z.-H., Mai, Z., Zhang, Z., Wu, Z., and Ma, Z.

Abstract

The Visual Object Tracking challenge VOT2020 is the eighth annual tracker benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The VOT2020 challenge was composed of five sub-challenges focusing on different tracking domains: (i) VOT-ST2020 challenge focused on short-term tracking in RGB, (ii) VOT-RT2020 challenge focused on “real-time” short-term tracking in RGB, (iii) VOT-LT2020 focused on long-term tracking namely coping with target disappearance and reappearance, (iv) VOT-RGBT2020 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2020 challenge focused on long-term tracking in RGB and depth imagery. Only the VOT-ST2020 datasets were refreshed. A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in the VOT-ST challenges. A new VOT Python toolkit that implements all these novelites was introduced. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net ).

Published
2020
Full Text
View/download PDF

11. The Seventh Visual Object Tracking VOT2019 Challenge Results

Author

Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R., Kämäräinen, J.-K., Čehovin Zajc, L., Drbohlav, O., Lukežič, A., Berg, A., Eldesokey, A., Käpylä, J., Fernández, G., Gonzalez-Garcia, A., Memarmoghadam, A., Lu, A., He, A., Varfolomieiev, A., Chan, A., Shekhar Tripathi, A., Smeulders, A., Suraj Pedasingu, B., Chen, B.X., Zhang, B., Wu, B., Li, B., He, B., Yan, B., Bai, B., Kim, B.H., Ma, C., Fang, C., Qian, C., Chen, C., Li, C., Zhang, C., Tsai, C.-Y., Luo, C., Micheloni, C., Tao, D., Gupta, D., Song, D., Wang, D., Gavves, E., Yi, E., Khan, F.S., Zhang, F., Wang, F., Zhao, F., De Ath, G., Bhat, G., Chen, G., Wang, G., Li, G., Cevikalp, H., Du, H., Zhao, H., Saribas, H., Jung, H.M., Bai, H., Hu, H., Peng, H., Lu, H., Li, H., Li, J., Fu, J., Chen, J., Gao, J., Zhao, J., Tang, J., Wu, J., Liu, J., Wang, J., Qi, J., Zhang, J., Tsotsos, J.K., Lee, J.H., van de Weijer, J., Kittler, J., Zhuang, J., Zhang, K., Wang, K., Dai, K., Chen, L., Liu, L., Guo, L., Zhang, L., Wang, L., Zhou, L., Zheng, L., Rout, L., Van Gool, L., Bertinetto, L., Danelljan, M., Dunnhofer, M., Ni, M., Kim, M.Y., Tang, M., Yang, M.-H., Paluru, N., Martinel, N., Xu, P., Zhang, P., Zheng, P., Torr, P.H.S., Zhang, Q., Wang, Q., Guo, Q., Timofte, R., Gorthi, R.K., Everson, R., Han, R., Zhang, R., You, S., Zhao, S.-C., Zhao, S., Li, S., Ge, S., Bai, S., Guan, S., Xing, T., Xu, T., Yang, T., Zhang, T., Vojíř, T., Feng, W., Hu, W., Wang, W., Tang, W., Zeng, W., Liu, W., Chen, X., Qiu, X., Bai, X., Wu, X.-J., Yang, X., Li, X., Sun, X., Tian, X., Tang, X., Zhu, X.-F., Huang, Y., Chen, Y., Lian, Y., Gu, Y., Liu, Y., Zhang, Y., Xu, Y., Wang, Y., Li, Y., Zhou, Y., Dong, Y., Wang, Z., Luo, Z., Zhang, Z., Feng, Z.-H., He, Z., Song, Z., Chen, Z., Wu, Z., Xiong, Z., Huang, Z., Teng, Z., Ni, Z., and Intelligent Sensory Information Systems (IVI, FNWI)

Subjects
Source code, Computer science, business.industry, media_common.quotation_subject, Object tracking, Performance evaluation, VOT challenge, 020206 networking & telecommunications, 02 engineering and technology, Visualization, Datorseende och robotik (autonoma system), Robustness (computer science), Video tracking, 0202 electrical engineering, electronic engineering, information engineering, RGB color model, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, Computer Vision and Robotics (Autonomous Systems), media_common
Abstract

The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2019 focused on long-term tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard short-term, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website(1). Funding Agencies|Slovenian research agencySlovenian Research Agency - Slovenia [J2-8175, P2-0214, P2-0094]; Czech Science Foundation Project GACR [P103/12/G084]; MURI project - MoD/DstlMURI; EPSRCEngineering & Physical Sciences Research Council (EPSRC) [EP/N019415/1]; WASP; VR (ELLIIT, LAST, and NCNN); SSF (SymbiCloud); AIT Strategic Research Programme; Faculty of Computer Science, University of Ljubljana, Slovenia

Published
2019

12. Applying artificial intelligence to assess the impact of orthognathic treatment on facial attractiveness and estimated age

Author

Patcas, R, Bernini, D A J, Volokitin, A, Agustsson, E, Rothe, R, Timofte, R, Patcas, R, Bernini, D A J, Volokitin, A, Agustsson, E, Rothe, R, and Timofte, R

Abstract

This observational study aimed to use artificial intelligence to describe the impact of orthognathic treatment on facial attractiveness and age appearance. Pre- and post-treatment photographs (n=2164) of 146 consecutive orthognathic patients were collected for this longitudinal retrospective single-centre study. Every image was annotated with patient-related data (age; sex; malocclusion; performed surgery). For every image, facial attractiveness (score: 0-100) and apparent age were established with dedicated convolutional neural networks trained on >0.5million images for age estimation and with >17million ratings for attractiveness. Results for pre- and post-treatment photographs were averaged for every patient separately, and apparent age compared to real age (appearance). Changes in appearance and facial attractiveness were statistically examined. Analyses were performed on the entire sample and subgroups (sex; malocclusion; performed surgery). According to the algorithms, most patients' appearance improved with treatment (66.4%), resulting in younger appearance of nearly 1year [mean change: -0.93years (95% confidence interval (CI): -1.50; -0.36); p=0.002), especially after profile-altering surgery. Orthognathic treatment had similarly a beneficial effect on attractiveness in 74.7% [mean difference: 1.22 (95% CI: 0.81; 1.63); p<0.001], especially after lower jaw surgery. This investigation illustrates that artificial intelligence might be considered to score facial attractiveness and apparent age in orthognathic patients.

Published
2019

13. NTIRE 2019 challenge on video super-resolution: methods and results

Author

Tekalp, Ahmet Murat (ORCID 0000-0003-1465-8121 & YÖK ID 26207), Nah, S.; Timofte, R.; Gu, S.; Baik, S.; Hong, S.; Moon, G.; Son, S.; Lee, K.M.; Wang, X.; Chan, K.C.K.; Yu, K.; Dong, C.; Loy, C.C.; Fan, Y.; Yu, J.; Liu, D.; Huang, T.S.; Liu, X.; Li, C.; He, D.; DIng, Y.; Wen, S.; Porikli, F.; Kalarot, R.; Haris, M.; Shakhnarovich, G.; Ukita, N.; Yi, P.; Wang, Z.; Jiang, K.; Jiang, J.; Ma, J.; Dong, H.; Zhang, X.; Hu, Z.; Kim, K.; Kang, D.U.; Chun, S.Y.; Purohit, K.; Rajagopalan, A.N.; Tian, Y.; Zhang, Y.; Fu, Y.; Xu, C.; Yılmaz, M.A.; Korkmaz, C.; Sharma, M.; Makwana, M.; Badhwar, A.; Singh, A.P.; Upadhyay, A.; Mukhopadhyay, R.; Shukla, A.; Khanna, D.; Mandal, A.S.; Chaudhury, S.; Miao, S.; Zhu, Y.; Huo, X., College of Engineering, Department of Electrical and Electronics Engineering, Tekalp, Ahmet Murat (ORCID 0000-0003-1465-8121 & YÖK ID 26207), Nah, S.; Timofte, R.; Gu, S.; Baik, S.; Hong, S.; Moon, G.; Son, S.; Lee, K.M.; Wang, X.; Chan, K.C.K.; Yu, K.; Dong, C.; Loy, C.C.; Fan, Y.; Yu, J.; Liu, D.; Huang, T.S.; Liu, X.; Li, C.; He, D.; DIng, Y.; Wen, S.; Porikli, F.; Kalarot, R.; Haris, M.; Shakhnarovich, G.; Ukita, N.; Yi, P.; Wang, Z.; Jiang, K.; Jiang, J.; Ma, J.; Dong, H.; Zhang, X.; Hu, Z.; Kim, K.; Kang, D.U.; Chun, S.Y.; Purohit, K.; Rajagopalan, A.N.; Tian, Y.; Zhang, Y.; Fu, Y.; Xu, C.; Yılmaz, M.A.; Korkmaz, C.; Sharma, M.; Makwana, M.; Badhwar, A.; Singh, A.P.; Upadhyay, A.; Mukhopadhyay, R.; Shukla, A.; Khanna, D.; Mandal, A.S.; Chaudhury, S.; Miao, S.; Zhu, Y.; Huo, X., College of Engineering, and Department of Electrical and Electronics Engineering

Abstract

This paper reviews the first NTIRE challenge on video super-resolution (restoration of rich details in low-resolution video frames) with focus on proposed solutions and results. A new REalistic and Diverse Scenes dataset (REDS) was employed. The challenge was divided into 2 tracks. Track 1 employed standard bicubic downscaling setup while Track 2 had realistic dynamic motion blurs. Each competition had 124 and 104 registered participants. There were total 14 teams in the final testing phase. They gauge the state-of-the-art in video super-resolution., NA

Published
2019

14. NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

Author

Timofte, R, Agustsson, E, Gool, LV, Yang, MH, Zhang, L, Lim, B, Son, S, Kim, H, Nah, S, Lee, KM, Wang, X, Tian, Y, Yu, K, Zhang, Y, Wu, S, Dong, C, Lin, L, Qiao, Y, Loy, CC, Bae, W, Yoo, J, Han, Y, Ye, JC, Choi, JS, Kim, M, Fan, Y, Yu, J, Han, W, Liu, D, Yu, H, Wang, Z, Shi, H, Huang, TS, Chen, Y, Zhang, K, Zuo, W, Tang, Z, Luo, L, Li, S, Fu, M, Cao, L, Heng, W, Bui, G, Le, T, Duan, Y, Tao, D, Wang, R, Lin, X, Pang, J, Xu, J, Zhao, Y, Xu, X, Pan, J, Sun, D, Song, X, Dai, Y, Qin, X, Huynh, XP, Guo, T, Mousavi, HS, Vu, TH, Monga, V, Cruz, C, Egiazarian, K, Katkovnik, V, Mehta, R, Jain, AK, Agarwalla, A, Praveen, CVS, Zhou, R, Wen, H, Zhu, C, Xia, Z, and Guo, Q

Subjects
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Abstract

© 2017 IEEE. This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had b∼100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

Published
2017

15. Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations

Author

Agustsson, E., Mentzer, F., Tschannen, M., Cavigelli, L., Timofte, R., LUCA BENINI, and Gool, L.

Subjects
FOS: Computer and information sciences, Computer Science - Learning, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Data_CODINGANDINFORMATIONTHEORY, Machine Learning (cs.LG)
Abstract

We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image compression and neural network compression. While these tasks have typically been approached with different methods, our soft-to-hard quantization approach gives results competitive with the state-of-the-art for both.

Published
2017
Full Text
View/download PDF

21. AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results

Author

Ren Yang, Radu Timofte, Xin Li, Qi Zhang, Lin Zhang, Fanglong Liu, Dongliang He, Fu Li, He Zheng, Weihang Yuan, Pavel Ostyakov, Dmitry Vyal, Magauiya Zhussip, Xueyi Zou, Youliang Yan, Lei Li, Jingzhu Tang, Ming Chen, Shijie Zhao, Yu Zhu, Xiaoran Qin, Chenghua Li, Cong Leng, Jian Cheng, Claudio Rota, Marco Buzzelli, Simone Bianco, Raimondo Schettini, Dafeng Zhang, Feiyu Huang, Shizhuo Liu, Xiaobing Wang, Zhezhu Jin, Bingchen Li, Mingxi Li, Ding Liu, Wenbin Zou, Peijie Dong, Tian Ye, Yunchen Zhang, Ming Tan, Xin Niu, Mustafa Ayazoglu, Marcos Conde, Ui-Jin Choi, Zhuang Jia, Tianyu Xu, Yijian Zhang, Mao Ye, Dengyan Luo, Xiaofeng Pan, Liuhan Peng, Karlinsky, L, Michaeli, T, Nishino, K, Yang, R, Timofte, R, Li, X, Zhang, Q, Zhang, L, Liu, F, He, D, Li, F, Zheng, H, Yuan, W, Ostyakov, P, Vyal, D, Zhussip, M, Zou, X, Yan, Y, Li, L, Tang, J, Chen, M, Zhao, S, Zhu, Y, Qin, X, Li, C, Leng, C, Cheng, J, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Zhang, D, Huang, F, Liu, S, Wang, X, Jin, Z, Li, B, Li, M, Liu, D, Zou, W, Dong, P, Ye, T, Zhang, Y, Tan, M, Niu, X, Ayazoglu, M, Conde, M, Choi, U, Jia, Z, Xu, T, Ye, M, Luo, D, Pan, X, and Peng, L

Subjects
Video compression, Image compression, Super-resolution
Abstract

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track 2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

Published
2023

22. NTIRE 2022 Challenge on Night Photography Rendering

Author

Egor Ershov, Alex Savchik, Denis Shepelev, Nikola Banic, Michael S. Brown, Radu Timofte, Karlo Koscevic, Michael Freeman, Vasily Tesalin, Dmitry Bocharov, Illya Semenkov, Marko Subasic, Sven Loncaric, Arseniy Terekhin, Shuai Liu, Chaoyu Feng, Hao Wang, Ran Zhu, Yongqiang Li, Lei Lei, Zhihao Li, Si Yi, Ling-Hao Han, Ruiqi Wu, Xin Jin, Chunle Guo, Furkan Kinli, Sami Mentes, Baris Ozcan, Furkan Kirac, Simone Zini, Claudio Rota, Marco Buzzelli, Simone Bianco, Raimondo Schettini, Wei Li, Yipeng Ma, Tao Wang, Ruikang Xu, Fenglong Song, Wei-Ting Chen, Hao-Hsiang Yang, Zhi-Kai Huang, Hua-En Chang, Sy-Yen Kuo, Zhexin Liang, Shangchen Zhou, Ruicheng Feng, Chongyi Li, Xiangyu Chen, Binbin Song, Shile Zhang, Lin Liu, Zhendong Wang, Dohoon Ryu, Hyokyoung Bae, Taesung Kwon, Chaitra Desai, Nikhil Akalwadi, Amogh Joshi, Chinmayee Mandi, Sampada Malagi, Akash Uppin, Sai Sudheer Reddy, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi, Ershov, E, Savchik, A, Shepelev, D, Banic, N, Brown, M, Timofte, R, Koscevic, K, Freeman, M, Tesalin, V, Bocharov, D, Semenkov, I, Subasic, M, Loncaric, S, Terekhin, A, Liu, S, Feng, C, Wang, H, Zhu, R, Li, Y, Lei, L, Li, Z, Yi, S, Han, L, Wu, R, Jin, X, Guo, C, Kinli, F, Mentes, S, Ozcan, B, Kirac, F, Zini, S, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Li, W, Ma, Y, Wang, T, Xu, R, Song, F, Chen, W, Yang, H, Huang, Z, Chang, H, Kuo, S, Liang, Z, Zhou, S, Feng, R, Li, C, Chen, X, Song, B, Zhang, S, Liu, L, Wang, Z, Ryu, D, Bae, H, Kwon, T, Desai, C, Akalwadi, N, Joshi, A, Mandi, C, Malagi, S, Uppin, A, Sudheer Reddy, S, Ashok Tabib, R, Patil, U, and Mudenagudi, U

Subjects
night photography, Photography, Visualization, Computer vision, Conferences, Rendering (computer graphics), Cameras, Pattern recognition
Abstract

This paper reviews the NTIRE 2022 challenge on night photography rendering. The challenge solicited solutions that processed RAW camera images captured in night scenes to produce a photo-finished output image encoded in the standard RGB (sRGB) space. Given the subjective nature of this task, the proposed solutions were evaluated based on the mean opinions of viewers asked to judge the visual appearance of the results. Michael Freeman, a world-renowned photographer, further ranked the solutions with the highest mean opinion scores. A total of 13 teams competed in the final phase of the challenge. The proposed methods provided by the participating teams represent state-of-the-art performance in nighttime photography. Results from the various teams can be found here: https://nightimaging.org/

Published
2022

23. NTIRE 2022 Spectral Recovery Challenge and Data Set

Author

Boaz Arad, Radu Timofte, Rony Yahel, Nimrod Morag, Amir Bernat, Yuanhao Cai, Jing Lin, Zudi Lin, Haoqian Wang, Yulun Zhang, Hanspeter Pfister, Luc Van Gool, Shuai Liu, Yongqiang Li, Chaoyu Feng, Lei Lei, Jiaojiao Li, Songcheng Du, Chaoxiong Wu, Yihong Leng, Rui Song, Mingwei Zhang, Chongxing Song, Shuyi Zhao, Zhiqiang Lang, Wei Wei, Lei Zhang, Renwei Dian, Tianci Shan, Anjing Guo, Chengguo Feng, Jinyang Liu, Mirko Agarla, Simone Bianco, Marco Buzzelli, Luigi Celona, Raimondo Schettini, Jiang He, Yi Xiao, Jiajun Xiao, Qiangqiang Yuan, Jie Li, Liangpei Zhang, Taesung Kwon, Dohoon Ryu, Hyokyoung Bae, Hao-Hsiang Yang, Hua-En Chang, Zhi-Kai Huang, Wei-Ting Chen, Sy-Yen Kuo, Junyu Chen, Haiwei Li, Song Liu, Sabarinathan Sabarinathan, K Uma, B Sathya Bama, S. Mohamed Mansoor Roomi, Arad, B, Timofte, R, Yahel, R, Morag, N, Bernat, A, Cai, Y, Lin, J, Lin, Z, Wang, H, Zhang, Y, Pfister, H, Van Gool, L, Liu, S, Li, Y, Feng, C, Lei, L, Li, J, Du, S, Wu, C, Leng, Y, Song, R, Zhang, M, Song, C, Zhao, S, Lang, Z, Wei, W, Zhang, L, Dian, R, Shan, T, Guo, A, Liu, J, Agarla, M, Bianco, S, Buzzelli, M, Celona, L, Schettini, R, He, J, Xiao, Y, Xiao, J, Yuan, Q, Kwon, T, Ryu, D, Bae, H, Yang, H, Chang, H, Huang, Z, Chen, W, Kuo, S, Chen, J, Li, H, Sabarinathan, S, Uma, K, Bama, B, and Roomi, S

Subjects
spectral reconstruction, spectral recovery
Abstract

This paper reviews the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. This challenge presents the "ARAD_1K"data set: a new, larger-than-ever natural hyperspectral image data set containing 1,000 images. Challenge participants were required to recover hyper-spectral information from synthetically generated JPEG-compressed RGB images simulating capture by a known calibrated camera, operating under partially known parameters, in a setting which includes acquisition noise. The challenge was attended by 241 teams, with 60 teams com-peting in the final testing phase, 12 of which provided de-tailed descriptions of their methodology which are included in this report. The performance of these submissions is re-viewed and provided here as a gauge for the current state-of-the-art in spectral reconstruction from natural RGB images.

Published
2022

24. NTIRE 2019 Challenge on Video Super-Resolution: Methods and Results

Author

Shuhang Gu, Greg Shakhnarovich, Fatih Porikli, Kyoung Mu Lee, Zhongyuan Wang, Yulun Zhang, Seokil Hong, M. Akin Yilmaz, Kuldeep Purohit, Si Miao, A. S. Mandal, Yapeng Tian, A. Murat Tekalp, Norimichi Ukita, Sanghyun Son, Junjun Jiang, Yun Fu, A.N. Rajagopalan, Chenliang Xu, Gyeongsik Moon, Sungyong Baik, Ankit Shukla, Zhe Hu, Chen Change Loy, Manoj Sharma, Chao Li, Ding Yukang, Dong Un Kang, Yongxin Zhu, Santanu Chaudhury, Ratheesh Kalarot, Hang Dong, Avinash Upadhyay, Muhammad Haris, Ke Yu, Thomas S. Huang, Megh Makwana, Wang Xintao, Xinyi Zhang, Peng Yi, Jiahui Yu, Kwanyoung Kim, Kui Jiang, Chao Dong, Xiao Huo, Rudrabha Mukhopadhyay, Yuchen Fan, Dongliang He, Ding Liu, Se Young Chun, Shilei Wen, Ajay Pratap Singh, Xiao Liu, Kelvin C.K. Chan, Cansu Korkmaz, Jiayi Ma, Radu Timofte, Anuj Badhwar, Seungjun Nah, Dheeraj Khanna, Tekalp, Ahmet Murat (ORCID 0000-0003-1465-8121 & YÖK ID 26207), Nah, S., Timofte, R., Gu, S., Baik, S., Hong, S., Moon, G., Son, S., Lee, K.M., Wang, X., Chan, K.C.K., Yu, K., Dong, C., Loy, C.C., Fan, Y., Yu, J., Liu, D., Huang, T.S., Liu, X., Li, C., He, D., DIng, Y., Wen, S., Porikli, F., Kalarot, R., Haris, M., Shakhnarovich, G., Ukita, N., Yi, P., Wang, Z., Jiang, K., Jiang, J., Ma, J., Dong, H., Zhang, X., Hu, Z., Kim, K., Kang, D.U., Chun, S.Y., Purohit, K., Rajagopalan, A.N., Tian, Y., Zhang, Y., Fu, Y., Xu, C., Yılmaz, M.A., Korkmaz, C., Sharma, M., Makwana, M., Badhwar, A., Singh, A.P., Upadhyay, A., Mukhopadhyay, R., Shukla, A., Khanna, D., Mandal, A.S., Chaudhury, S., Miao, S., Zhu, Y., Huo, X., College of Engineering, and Department of Electrical and Electronics Engineering

Subjects
Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Image resolution, Image restoration, Video signal processing, Track (rail transport), Superresolution, Optical resolving power, Image super, 0202 electrical engineering, electronic engineering, information engineering, Bicubic interpolation, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Focus (optics), business
Abstract

This paper reviews the first NTIRE challenge on video super-resolution (restoration of rich details in low-resolution video frames) with focus on proposed solutions and results. A new REalistic and Diverse Scenes dataset (REDS) was employed. The challenge was divided into 2 tracks. Track 1 employed standard bicubic downscaling setup while Track 2 had realistic dynamic motion blurs. Each competition had 124 and 104 registered participants. There were total 14 teams in the final testing phase. They gauge the state-of-the-art in video super-resolution., NA

Published
2019

25. NTIRE 2019 challenge on image enhancement: Methods and results

Author

Ling Shao, Liang Lin, Flavio Piccoli, Xingguang Zhou, Dongwon Park, Syed Waqas Zamir, Lai-Kuan Wong, Greg Shakhnarovich, Cheolkon Jung, Hongzhi Zhang, Andrey Ignatov, Xiaochao Qu, Pengxu Wei, Zhiwei Zhong, Zheng Hui, Kazutoshi Akita, Jinghui Qin, Xinbo Gao, Pablo Navarrete Michelini, Wushao Wen, Jingdong Liu, Radu Timofte, Jie Liu, Jiye Liu, Salman Khan, Norimichi Ukita, Hanwen Liu, Wangmeng Zuo, Muhammad Haris, Yukai Shi, Debin Zhao, Fahad Shahbaz Khan, Pengfei Wan, Ganapathy Krishnamurthi, Xianming Liu, Se Young Chun, Simone Bianco, Tomoki Yoshida, Ting Liu, Xiumei Wang, Kai Zhang, Junjun Jiang, Claudio Cusano, John See, Nelson Chong Ngee Bow, Lishan Huang, Pengju Liu, Raimondo Schettini, Mahendra Khened, Kanti Kumari, Aditya Arora, Vikas Kumar Anand, Dan Zhu, Ignatov, A, Timofte, R, Qu, X, Zhou, X, Liu, T, Wan, P, Zamir, S, Arora, A, Khan, S, Khan, F, Shao, L, Park, D, Chun, S, Michelini, P, Liu, H, Zhu, D, Zhong, Z, Liu, X, Jiang, J, Zhao, D, Haris, M, Akita, K, Yoshida, T, Shakhnarovich, G, Ukita, N, Liu, J, Jung, C, Schettini, R, Bianco, S, Cusano, C, Piccoli, F, Liu, P, Zhang, K, Zhang, H, Zuo, W, Bow, N, Wong, L, See, J, Qin, J, Huang, L, Shi, Y, Wei, P, Wen, W, Lin, L, Hui, Z, Wang, X, Gao, X, Kumari, K, Anand, V, Khened, M, and Krishnamurthi, G

Subjects
0209 industrial biotechnology, Computer science, Image quality, Structural similarity, business.industry, media_common.quotation_subject, image enhancement, image quality, tone adjustment, cameras, smartphones, task analysis, visualization, computer vision, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Visualization, Image (mathematics), 020901 industrial engineering & automation, Perception, Metric (mathematics), 0202 electrical engineering, electronic engineering, information engineering, Contrast (vision), 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, Focus (optics), Image resolution, media_common
Abstract

This paper reviews the first NTIRE challenge on perceptual image enhancement with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with Canon 70D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image denoising, image resolution and sharpness enhancement, image color/contrast/exposure adjustment, etc. The target metric used in this challenge combined PSNR and SSIM scores with solutions' perceptual results measured in the user study. The proposed solutions significantly improved baseline results, defining the state-of-the-art for practical image enhancement.

Published
2019

26. NTIRE 2019 challenge on real image denoising: Methods and results

Author

Kazutoshi Akita, Thomas S. Huang, Simone Zini, Raimondo Schettini, Jae-Ryun Chung, Bumjun Park, Chuan Wang, Sang-Won Lee, Seung-Won Jung, Simone Bianco, Lei Zhang, Yiyun Zhao, Yuchen Fan, Yifan Ding, Greg Shakhnarovich, Se Young Chun, Hongwei Yong, Ling Shao, Deyu Meng, Wangmeng Zuo, Chi Li, Salman Khan, Tomoki Yoshida, Chang Chen, Ding Liu, Dongwon Park, Wenyi Tang, Zhiwei Xiong, Syed Waqas Zamir, Yuqian Zhou, Norimichi Ukita, Haoqiang Fan, Seung-Wook Kim, Jue Wang, Zhiguo Cao, Yuzhi Wang, Radu Timofte, Dong-Wook Kim, Sung-Jea Ko, Fahad Shahbaz Khan, Magauiya Zhussip, Dong-Pan Lim, Seo-Won Ji, Yang Wang, Muhammad Haris, Aditya Arora, Michael S. Brown, Shakarim Soltanayev, Jiaming Liu, Qin Xu, Abdelrahman Abdelhamed, Shaofan Cai, Kai Zhang, Jechang Jeong, Chi-Hao Wu, Songhyun Yu, Yue Lu, Pengliang Tang, Abdelhamed, A, Timofte, R, Brown, M, Yu, S, Park, B, Jeong, J, Jung, S, Kim, D, Chung, J, Liu, J, Wang, Y, Wu, C, Xu, Q, Wang, C, Cai, S, Ding, Y, Fan, H, Wang, J, Zhang, K, Zuo, W, Zhussip, M, Park, D, Soltanayev, S, Chun, S, Xiong, Z, Chen, C, Haris, M, Akita, K, Yoshida, T, Shakhnarovich, G, Ukita, N, Zamir, S, Arora, A, Khan, S, Khan, F, Shao, L, Ko, S, Lim, D, Kim, S, Ji, S, Lee, S, Tang, W, Fan, Y, Zhou, Y, Liu, D, Huang, T, Meng, D, Zhang, L, Yong, H, Zhao, Y, Tang, P, Lu, Y, Schettini, R, Bianco, S, Zini, S, Li, C, and Cao, Z

Subjects
Noise measurement, Computer science, business.industry, Noise reduction, sRGB, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 0211 other engineering and technologies, INF/01 - INFORMATICA, 02 engineering and technology, Color space, Real image, Image denoising, 0202 electrical engineering, electronic engineering, information engineering, RGB color model, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Focus (optics), business, 021101 geological & geomatics engineering
Abstract

This paper reviews the NTIRE 2019 challenge on real image denoising with focus on the proposed methods and their results. The challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern raw-RGB and (2) the standard RGB (sRGB) color spaces. The tracks had 216 and 220 registered participants, respectively. A total of 15 teams, proposing 17 methods, competed in the final phase of the challenge. The proposed methods by the 15 teams represent the current state-of-the-art performance in image denoising targeting real noisy images.

Published
2019

27. Efficient End-to-End Convolutional Architecture for Point-of-Gaze Estimation.

Author

Miron C, Ciubotariu G, Păsărică A, and Timofte R

Abstract

Point-of-gaze estimation is part of a larger set of tasks aimed at improving user experience, providing business insights, or facilitating interactions with different devices. There has been a growing interest in this task, particularly due to the need for upgrades in e-meeting platforms during the pandemic when on-site activities were no longer possible for educational institutions, corporations, and other organizations. Current research advancements are focusing on more complex methodologies for data collection and task implementation, creating a gap that we intend to address with our contributions. Thus, we introduce a methodology for data acquisition that shows promise due to its nonrestrictive and straightforward nature, notably increasing the yield of collected data without compromising diversity or quality. Additionally, we present a novel and efficient convolutional neural network specifically tailored for calibration-free point-of-gaze estimation that outperforms current state-of-the-art methods on the MPIIFaceGaze dataset by a substantial margin, and sets a strong baseline on our own data.

Published
2024
Full Text
View/download PDF

28. High-Precision Dichotomous Image Segmentation With Frequency and Scale Awareness.

Author

Jiang Q, Cheng J, Wu Z, Cong R, and Timofte R

Abstract

Dichotomous image segmentation (DIS) with rich fine-grained details within a single image is a challenging task. Despite the plausible results achieved by deep learning-based methods, most of them fail to segment generic objects when the boundary is cluttered with the background. In fact, the gradual decrease in feature map resolution during the encoding stage and the misleading texture clue may be the main issues. To handle these issues, we devise a novel frequency-and scale-aware deep neural network (FSANet) for high-precision DIS. The core of our proposed FSANet is twofold. First, a multimodality fusion (MF) module that integrates the information in spatial and frequency domains is adopted to enhance the representation capability of image features. Second, a collaborative scale fusion module (CSFM) which deviates from the traditional serial structures is introduced to maintain high resolution during the entire feature encoding stage. In the decoder side, we introduce hierarchical context fusion (HCF) and selective feature fusion (SFF) modules to infer the segmentation results from the output features of the CSFM module. We conduct extensive experiments on several benchmark datasets and compare our proposed method with existing state-of-the-art (SOTA) methods. The experimental results demonstrate that our FSANet achieves superior performance both qualitatively and quantitatively. The code will be made available at https://github.com/chasecjg/FSANet.

Published
2024
Full Text
View/download PDF

29. Scoring facial attractiveness with deep convolutional neural networks: How training on standardized images reduces the bias of facial expressions.

Author

Obwegeser D, Timofte R, Mayer C, Bornstein MM, Schätzle MA, and Patcas R

Abstract

Objective: In many medical disciplines, facial attractiveness is part of the diagnosis, yet its scoring might be confounded by facial expressions. The intent was to apply deep convolutional neural networks (CNN) to identify how facial expressions affect facial attractiveness and to explore whether a dedicated training of the CNN is able to reduce the bias of facial expressions., Materials and Methods: Frontal facial images (n = 840) of 40 female participants (mean age 24.5 years) were taken adapting a neutral facial expression and the six universal facial expressions. Facial attractiveness was computed by means of a face detector, deep convolutional neural networks, standard support vector regression for facial beauty, visual regularized collaborative filtering and a regression technique for handling visual queries without rating history. CNN was first trained on random facial photographs from a dating website and then further trained on the Chicago Face Database (CFD) to increase its suitability to medical conditions. Both algorithms scored every image for attractiveness., Results: Facial expressions affect facial attractiveness scores significantly. Scores from CNN additionally trained on CFD had less variability between the expressions (range 54.3-60.9 compared to range: 32.6-49.5) and less variance within the scores (P ≤ .05), but also caused a shift in the ranking of the expressions' facial attractiveness., Conclusion: Facial expressions confound attractiveness scores. Training on norming images generated scores less susceptible to distortion, but more difficult to interpret. Scoring facial attractiveness based on CNN seems promising, but AI solutions must be developed on CNN trained to recognize facial expressions as distractors., (© 2024 The Author(s). Orthodontics & Craniofacial Research published by John Wiley & Sons Ltd.)

Published
2024
Full Text
View/download PDF

30. VRT: A Video Restoration Transformer.

Author

Liang J, Cao J, Fan Y, Zhang K, Ranjan R, Li Y, Timofte R, and Van Gool L

Abstract

Video restoration aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple adjacent but usually misaligned video frames. Existing deep methods generally tackle with this by exploiting a sliding window strategy or a recurrent architecture, which are restricted by frame-by-frame restoration. In this paper, we propose a Video Restoration Transformer (VRT) with parallel frame prediction ability. More specifically, VRT is composed of multiple scales, each of which consists of two kinds of modules: temporal reciprocal self attention (TRSA) and parallel warping. TRSA divides the video into small clips, on which reciprocal attention is applied for joint motion estimation, feature alignment and feature fusion, while self attention is used for feature extraction. To enable cross-clip interactions, the video sequence is shifted for every other layer. Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping. Experimental results on five tasks, including video super-resolution, video deblurring, video denoising, video frame interpolation and space-time video super-resolution, demonstrate that VRT outperforms the state-of-the-art methods by large margins (up to 2.16dB) on fourteen benchmark datasets. The codes are available at https://github.com/JingyunLiang/VRT.

Published
2024
Full Text
View/download PDF

31. PDC-Net+: Enhanced Probabilistic Dense Correspondence Network.

Author

Truong P, Danelljan M, Timofte R, and Van Gool L

Subjects
Algorithms, Pattern Recognition, Automated methods
Abstract

Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling alternative paradigm that avoids the keypoint detection step. However, dense flow estimation is often inaccurate in the case of large displacements, occlusions, or homogeneous regions. In order to apply dense methods to real-world applications, such as pose estimation, image manipulation, or 3D reconstruction, it is therefore crucial to estimate the confidence of the predicted matches. We propose the Enhanced Probabilistic Dense Correspondence Network, PDC-Net+, capable of estimating accurate dense correspondences along with a reliable confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. In particular, we parametrize the predictive distribution as a constrained mixture model, ensuring better modelling of both accurate flow predictions and outliers. Moreover, we develop an architecture and an enhanced training strategy tailored for robust and generalizable uncertainty prediction in the context of self-supervised training. Our approach obtains state-of-the-art results on multiple challenging geometric matching and optical flow datasets. We further validate the usefulness of our probabilistic confidence estimation for the tasks of pose estimation, 3D reconstruction, image-based localization, and image retrieval.

Published
2023
Full Text
View/download PDF

32. Learning Context-Based Nonlocal Entropy Modeling for Image Compression.

Author

Li M, Zhang K, Li J, Zuo W, Timofte R, and Zhang D

Abstract

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in reducing the entropy and boosting the joint rate-distortion performance. However, existing deep learning based entropy models generally assume the latent codes are statistically independent or depend on some side information or local context, which fails to take the global similarity within the context into account and thus hinders the accurate entropy estimation. To address this issue, we propose a special nonlocal operation for context modeling by employing the global similarity within the context. Specifically, due to the constraint of context, nonlocal operation is incalculable in context modeling. We exploit the relationship between the code maps produced by deep neural networks and introduce the proxy similarity functions as a workaround. Then, we combine the local and the global context via a nonlocal attention block and employ it in masked convolutional networks for entropy modeling. Taking the consideration that the width of the transforms is essential in training low distortion models, we finally produce a U-net block in the transforms to increase the width with manageable memory consumption and time complexity. Experiments on Kodak and Tecnick datasets demonstrate the priority of the proposed context-based nonlocal attention block in entropy modeling and the U-net block in low distortion situations. On the whole, our model performs favorably against the existing image compression standards and recent deep image compression models.

Published
2023
Full Text
View/download PDF

33. Artificial intelligence in medico-dental diagnostics of the face: a narrative review of opportunities and challenges.

Author

Patcas R, Bornstein MM, Schätzle MA, and Timofte R

Subjects
Humans, Artificial Intelligence
Abstract

Objectives: This review aims to share the current developments of artificial intelligence (AI) solutions in the field of medico-dental diagnostics of the face. The primary focus of this review is to present the applicability of artificial neural networks (ANN) to interpret medical images, together with the associated opportunities, obstacles, and ethico-legal concerns., Material and Methods: Narrative literature review., Results: Narrative literature review., Conclusion: Curated facial images are widely available and easily accessible and are as such particularly suitable big data for ANN training. New AI solutions have the potential to change contemporary dentistry by optimizing existing processes and enriching dental care with the introduction of new tools for assessment or treatment planning. The analyses of health-related big data may also contribute to revolutionize personalized medicine through the detection of previously unknown associations. In regard to facial images, advances in medico-dental AI-based diagnostics include software solutions for the detection and classification of pathologies, for rating attractiveness and for the prediction of age or gender. In order for an ANN to be suitable for medical diagnostics of the face, the arising challenges regarding computation and management of the software are discussed, with special emphasis on the use of non-medical big data for ANN training. The legal and ethical ramifications of feeding patients' facial images to a neural network for diagnostic purposes are related to patient consent, data privacy, data security, liability, and intellectual property. Current ethico-legal regulation practices seem incapable of addressing all concerns and ensuring accountability., Clinical Significance: While this review confirms the many benefits derived from AI solutions used for the diagnosis of medical images, it highlights the evident lack of regulatory oversight, the urgent need to establish licensing protocols, and the imperative to investigate the moral quality of new norms set with the implementation of AI applications in medico-dental diagnostics., (© 2022. The Author(s).)

Published
2022
Full Text
View/download PDF

34. Plug-and-Play Image Restoration With Deep Denoiser Prior.

Author

Zhang K, Li Y, Zuo W, Zhang L, Van Gool L, and Timofte R

Abstract

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a property induces considerable advantages for plug-and-play image restoration (e.g., integrating the flexibility of model-based method and effectiveness of learning-based methods) when the denoiser is discriminatively learned via deep convolutional neural network (CNN) with large modeling capacity. However, while deeper and larger CNN models are rapidly gaining popularity, existing plug-and-play image restoration hinders its performance due to the lack of suitable denoiser prior. In order to push the limits of plug-and-play image restoration, we set up a benchmark deep denoiser prior by training a highly flexible and effective CNN denoiser. We then plug the deep denoiser prior as a modular part into a half quadratic splitting based iterative algorithm to solve various image restoration problems. We, meanwhile, provide a thorough analysis of parameter setting, intermediate results and empirical convergence to better understand the working mechanism. Experimental results on three representative image restoration tasks, including deblurring, super-resolution and demosaicing, demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state-of-the-art learning-based methods. The source code is available at https://github.com/cszn/DPIR.

Published
2022
Full Text
View/download PDF

35. Using artificial intelligence to determine the influence of dental aesthetics on facial attractiveness in comparison to other facial modifications.

Author

Obwegeser D, Timofte R, Mayer C, Eliades T, Bornstein MM, Schätzle MA, and Patcas R

Subjects
Adult, Esthetics, Dental, Face, Female, Humans, Index of Orthodontic Treatment Need, Infant, Smiling, Young Adult, Artificial Intelligence, Malocclusion therapy
Abstract

Background: Facial aesthetics is a major motivating factor for undergoing orthodontic treatment., Objectives: To ascertain-by means of artificial intelligence (AI)-the influence of dental alignment on facial attractiveness and perceived age, compared to other modifications such as wearing glasses, earrings, or lipstick., Material and Methods: Forty volunteering females (mean age: 24.5) with near perfectly aligned upper front teeth [Aesthetic Component scale of the Index of Orthodontic Treatment Need (AC-IOTN) = 1 and Peer Assessment Rating Index (PAR Index) = 0 or 1] were photographed with a standardized pose while smiling, in the following settings (number of photographs = 960): without modifications, wearing eyeglasses, earrings, or lipstick. These pictures were taken with natural aligned dentition and with an individually manufactured crooked teeth mock-up (AC-IOTN = 8) to create the illusion of misaligned teeth. Images were assessed for attractiveness and perceived age, using AI, consisting of a face detector and deep convolutional neural networks trained on dedicated datasets for attractiveness and age prediction. Each image received an attractiveness score from 0 to 100 and one value for an age prediction. The scores were descriptively reviewed for each setting, and the facial modifications were tested statistically whether they affected the attractiveness score. The relationship between predicted age and attractiveness scores was examined with linear regression models., Results: All modifications showed a significant effect (for all: P &lt; 0.001) on facial attractiveness. In faces with misaligned teeth, wearing eyeglasses (-17.8%) and earrings (-3.2%) had an adverse effect on facial aesthetics. Tooth alignment (+6.9%) and wearing lipstick (+7.9%) increased attractiveness. There was no relevant effect of any assessed modifications or tooth alignment on perceived age (all: &lt;1.5 years). Mean attractiveness score declined with predicted age, except when wearing glasses, in which case attractiveness was rated higher with increasing predicted age., Conclusions: Alignment of teeth improves facial attractiveness to a similar extent than wearing lipstick, but has no discernable effect on perceived age. Wearing glasses reduces attractiveness considerably, but this effect vanishes with age., (© The Author(s) 2022. Published by Oxford University Press on behalf of the European Orthodontic Society. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Published
2022
Full Text
View/download PDF

36. Outdoor Plant Segmentation With Deep Learning for High-Throughput Field Phenotyping on a Diverse Wheat Dataset.

Author

Zenkl R, Timofte R, Kirchgessner N, Roth L, Hund A, Van Gool L, Walter A, and Aasen H

Abstract

Robust and automated segmentation of leaves and other backgrounds is a core prerequisite of most approaches in high-throughput field phenotyping. So far, the possibilities of deep learning approaches for this purpose have not been explored adequately, partly due to a lack of publicly available, appropriate datasets. This study presents a workflow based on DeepLab v3+ and on a diverse annotated dataset of 190 RGB (350 x 350 pixels) images. Images of winter wheat plants of 76 different genotypes and developmental stages have been acquired throughout multiple years at high resolution in outdoor conditions using nadir view, encompassing a wide range of imaging conditions. Inconsistencies of human annotators in complex images have been quantified, and metadata information of camera settings has been included. The proposed approach achieves an intersection over union (IoU) of 0.77 and 0.90 for plants and soil, respectively. This outperforms the benchmarked machine learning methods which use Support Vector Classifier and/or Random Forrest. The results show that a small but carefully chosen and annotated set of images can provide a good basis for a powerful segmentation pipeline. Compared to earlier methods based on machine learning, the proposed method achieves better performance on the selected dataset in spite of using a deep learning approach with limited data. Increasing the amount of publicly available data with high human agreement on annotations and further development of deep neural network architectures will provide high potential for robust field-based plant segmentation in the near future. This, in turn, will be a cornerstone of data-driven improvement in crop breeding and agricultural practices of global benefit., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Zenkl, Timofte, Kirchgessner, Roth, Hund, Van Gool, Walter and Aasen.)

Published
2022
Full Text
View/download PDF

37. Learned Dynamic Guidance for Depth Image Reconstruction.

Author

Gu S, Guo S, Zuo W, Chen Y, Timofte R, Van Gool L, and Zhang L

Abstract

The depth images acquired by consumer depth sensors (e.g., Kinect and ToF) usually are of low resolution and insufficient quality. One natural solution is to incorporate a high resolution RGB camera and exploit the statistical correlation of its data and depth. In recent years, both optimization-based and learning-based approaches have been proposed to deal with the guided depth reconstruction problems. In this paper, we introduce a weighted analysis sparse representation (WASR) model for guided depth image enhancement, which can be considered a generalized formulation of a wide range of previous optimization-based models. We unfold the optimization by the WASR model and conduct guided depth reconstruction with dynamically changed stage-wise operations. Such a guidance strategy enables us to dynamically adjust the stage-wise operations that update the depth image, thus improving the reconstruction quality and speed. To learn the stage-wise operations in a task-driven manner, we propose two parameterizations and their corresponding methods: dynamic guidance with Gaussian RBF nonlinearity parameterization (DG-RBF) and dynamic guidance with CNN nonlinearity parameterization (DG-CNN). The network structures of the proposed DG-RBF and DG-CNN methods are designed with the the objective function of our WASR model in mind and the optimal network parameters are learned from paired training data. Such optimization-inspired network architectures enable our models to leverage the previous expertise as well as take benefit from training data. The effectiveness is validated for guided depth image super-resolution and for realistic depth image reconstruction tasks using standard benchmarks. Our DG-RBF and DG-CNN methods achieve the best quantitative results (RMSE) and better visual quality than the state-of-the-art approaches at the time of writing. The code is available at https://github.com/ShuhangGu/GuidedDepthSR.

Published
2019
Full Text
View/download PDF

38. Facial attractiveness of cleft patients: a direct comparison between artificial-intelligence-based scoring and conventional rater groups.

Author

Patcas R, Timofte R, Volokitin A, Agustsson E, Eliades T, Eichenberger M, and Bornstein MM

Subjects
Adult, Humans, Intelligence, Male, Young Adult, Artificial Intelligence, Face
Abstract

Objectives: To evaluate facial attractiveness of treated cleft patients and controls by artificial intelligence (AI) and to compare these results with panel ratings performed by laypeople, orthodontists, and oral surgeons., Materials and Methods: Frontal and profile images of 20 treated left-sided cleft patients (10 males, mean age: 20.5 years) and 10 controls (5 males, mean age: 22.1 years) were evaluated for facial attractiveness with dedicated convolutional neural networks trained on >17 million ratings for attractiveness and compared to the assessments of 15 laypeople, 14 orthodontists, and 10 oral surgeons performed on a visual analogue scale (n = 2323 scorings)., Results: AI evaluation of cleft patients (mean score: 4.75 ± 1.27) was comparable to human ratings (laypeople: 4.24 ± 0.81, orthodontists: 4.82 ± 0.94, oral surgeons: 4.74 ± 0.83) and was not statistically different (all Ps ≥ 0.19). Facial attractiveness of controls was rated significantly higher by humans than AI (all Ps ≤ 0.02), which yielded lower scores than in cleft subjects. Variance was considerably large in all human rating groups when considering cases separately, and especially accentuated in the assessment of cleft patients (coefficient of variance-laypeople: 38.73 ± 9.64, orthodontists: 32.56 ± 8.21, oral surgeons: 42.19 ± 9.80)., Conclusions: AI-based results were comparable with the average scores of cleft patients seen in all three rating groups (with especially strong agreement to both professional panels) but overall lower for control cases. The variance observed in panel ratings revealed a large imprecision based on a problematic absence of unity., Implication: Current panel-based evaluations of facial attractiveness suffer from dispersion-related issues and remain practically unavailable for patients. AI could become a helpful tool to describe facial attractiveness, but the present results indicate that important adjustments are needed on AI models, to improve the interpretation of the impact of cleft features on facial attractiveness., (© The Author(s) 2019. Published by Oxford University Press on behalf of the European Orthodontic Society. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Published
2019
Full Text
View/download PDF

39. Demosaicing Based on Directional Difference Regression and Efficient Regression Priors.

Author

Wu J, Timofte R, and Van Gool L

Subjects
Artifacts, Colorimetry, Algorithms, Image Enhancement, Image Interpretation, Computer-Assisted
Abstract

Color demosaicing is a key image processing step aiming to reconstruct the missing pixels from a recorded raw image. On the one hand, numerous interpolation methods focusing on spatial-spectral correlations have been proved very efficient, whereas they yield a poor image quality and strong visible artifacts. On the other hand, optimization strategies, such as learned simultaneous sparse coding and sparsity and adaptive principal component analysis-based algorithms, were shown to greatly improve image quality compared with that delivered by interpolation methods, but unfortunately are computationally heavy. In this paper, we propose efficient regression priors as a novel, fast post-processing algorithm that learns the regression priors offline from training data. We also propose an independent efficient demosaicing algorithm based on directional difference regression, and introduce its enhanced version based on fused regression. We achieve an image quality comparable to that of the state-of-the-art methods for three benchmarks, while being order(s) of magnitude faster.

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results