1,883 results on '"image inpainting"'
Search Results
2. Removing visual occlusion of construction scaffolds via a two-step method combining semantic segmentation and image inpainting
- Author
-
Ding, Yuexiong, Liu, Muyang, Zhang, Ming, and Luo, Xiaowei
- Published
- 2025
- Full Text
- View/download PDF
Catalog
3. IE-NeRF: Exploring transient mask inpainting to enhance neural radiance fields in the wild
- Author
-
Wang, Shuaixian, Xu, Haoran, Li, Yaokun, Chen, Jiwei, and Tan, Guang
- Published
- 2025
- Full Text
- View/download PDF
4. Do inpainting yourself: Generative facial inpainting guided by exemplars
- Author
-
Lu, Wanglong, Zhao, Hanli, Jiang, Xianta, Jin, Xiaogang, Yang, Yong-Liang, and Shi, Kaijie
- Published
- 2025
- Full Text
- View/download PDF
5. Image inpainting based on CNN-Transformer framework via structure and texture restoration
- Author
-
Li, Zhan, Han, Nan, Wang, Yuning, Zhang, Yanan, Yan, Jing, Du, Yingfei, and Geng, Guohua
- Published
- 2025
- Full Text
- View/download PDF
6. FloorDiffusion: Diffusion model-based conditional floorplan image generation method using parameter-efficient fine-tuning and image inpainting
- Author
-
Shim, Jonghwa, Moon, Jaeuk, Kim, Hyeonwoo, and Hwang, Eenjun
- Published
- 2024
- Full Text
- View/download PDF
7. Structural Information-Guided Fine-Grained Texture Image Inpainting
- Author
-
Fang, Zhiyi, Qian, Yi, Dai, Xiyue, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Ide, Ichiro, editor, Kompatsiaris, Ioannis, editor, Xu, Changsheng, editor, Yanai, Keiji, editor, Chu, Wei-Ta, editor, Nitta, Naoko, editor, Riegler, Michael, editor, and Yamasaki, Toshihiko, editor more...
- Published
- 2025
- Full Text
- View/download PDF
8. GAN-Based Image Inpainting Using Modified Gated Convolution
- Author
-
Devi Arumugam, Cynthia, Banothu, Balaji, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Kumar Singh, Koushlendra, editor, Singh, Sangeeta, editor, Srivastava, Subodh, editor, and Bajpai, Manish Kumar, editor more...
- Published
- 2025
- Full Text
- View/download PDF
9. Enhancing Multimedia Applications by Removing Dynamic Objects in Neural Radiance Fields
- Author
-
Yang, XianBen, Wang, Tao, Liu, He, Jin, Yi, Lang, Congyan, Li, Yidong, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Cho, Minsu, editor, Laptev, Ivan, editor, Tran, Du, editor, Yao, Angela, editor, and Zha, Hongbin, editor more...
- Published
- 2025
- Full Text
- View/download PDF
10. BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
- Author
-
Ju, Xuan, Liu, Xian, Wang, Xintao, Bian, Yuxuan, Shan, Ying, Xu, Qiang, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor more...
- Published
- 2025
- Full Text
- View/download PDF
11. A Task Is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
- Author
-
Zhuang, Junhao, Zeng, Yanhong, Liu, Wenran, Yuan, Chun, Chen, Kai, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor more...
- Published
- 2025
- Full Text
- View/download PDF
12. SAIR: Learning Semantic-Aware Implicit Representation
- Author
-
Zhang, Canyu, Li, Xiaoguang, Guo, Qing, Wang, Song, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Leonardis, Aleš, editor, Ricci, Elisa, editor, Roth, Stefan, editor, Russakovsky, Olga, editor, Sattler, Torsten, editor, and Varol, Gül, editor more...
- Published
- 2025
- Full Text
- View/download PDF
13. Residual trio feature network for efficient super-resolution.
- Author
-
Chen, Junfeng, Mao, Mao, Guan, Azhu, and Ayush, Altangerel
- Abstract
Deep learning-based approaches have demonstrated impressive performance in single-image super-resolution (SISR). Efficient super-resolution compromises the reconstructed image’s quality to have fewer parameters and Flops. Ensured efficiency in image reconstruction and improved reconstruction quality of the model are significant challenges. This paper proposes a trio branch module (TBM) based on structural reparameterization. TBM achieves equivalence transformation through structural reparameterization operations, which use a complex network structure in the training phase and convert it to a more lightweight structure in the inference, achieving efficient inference while maintaining accuracy. Based on the TBM, we further design a lightweight version of the enhanced spatial attention mini (ESA-mini) and the residual trio feature block (RTFB). Moreover, the multiple RTFBs are combined to construct the residual trio network (RTFN). Finally, we introduce a localized contrast loss for better applicability to the super-resolution task, which enhances the reconstruction quality of the super-resolution model. Experiments show that the RTFN framework proposed in this paper outperforms other state-of-the-art efficient super-resolution methods in terms of inference speed and reconstruction quality. [ABSTRACT FROM AUTHOR] more...
- Published
- 2025
- Full Text
- View/download PDF
14. Elastic bending total variation model for image inpainting with operator splitting method.
- Author
-
Nan, Caixia and Zhang, Qian
- Subjects
- *
INPAINTING , *IMAGE processing , *ALGORITHMS , *LIPIDS - Abstract
The elastic bending energy model is commonly used to describe the shape transformation of biological lipid vesicles, making it a classical phase field model. In this paper, by coupling the elastic bending energy with the total variation (TV) regularization, we develop an elastic bending-TV model for image inpainting. By solving the energy minimization problem of this model, we obtain the results for image processing. We adopt an operator splitting method for the model and the numerical scheme involves the introduction of two vector- and scalar-valued functions to reconstruct this functional. The energy minimization problem is transformed into finding the steady state solution of artificial time-dependent PDE systems. At each fractional step, we can find either a closed-form solution or being solved by an efficient algorithm, which is a very robust and stable algorithm. Experimental results validate the superiority of our model and the effectiveness of the scheme for image inpainting. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
15. Unified Domain Adaptation for Specialized Indoor Scene Inpainting Using a Pre-Trained Model.
- Author
-
Akter, Asrafi and Lee, Myungho
- Subjects
CONVOLUTIONAL neural networks ,ARTIFICIAL neural networks ,IMAGE reconstruction ,IMAGE processing ,IMAGING systems - Abstract
Image inpainting for indoor environments presents unique challenges due to complex spatial relationships, diverse lighting conditions, and domain-specific object configurations. This paper introduces a resource-efficient post-processing framework that enhances domain-specific image inpainting through an adaptation mechanism. Our architecture integrates a convolutional neural network with residual connections optimized via a multi-term objective function combining perceptual losses and adaptive loss weighting. Experiments on our curated dataset of 4000 indoor household scenes demonstrate improved performance, with training completed in 20 min on commodity GPU hardware with 0.14 s of inference latency per image. The framework exhibits enhanced results across standard metrics (FID, SSIM, LPIPS, MAE, and PSNR), showing improvements in structural coherence and perceptual quality while preserving cross-domain generalization abilities. Our methodology offers a novel approach for efficient domain adaptation in image inpainting, particularly suitable for real-world applications under computational constraints. This work advances the development of domain-aware image restoration systems and provides architectural insights for specialized image processing frameworks. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
16. TSFormer: Tracking Structure Transformer for Image Inpainting.
- Author
-
Lin, Jiayu and Wang, Yuan-Gen
- Subjects
INPAINTING ,HISTOGRAMS ,SWINE ,DESIGN - Abstract
Recent studies have shown that image structure can significantly facilitate image inpainting. However, current approaches mostly explore structure prior without considering its guidance to texture reconstruction, leading to performance degradation. To solve this issue, we propose a two-stream Tracking Structure Transformer (TSFormer), including structure target stream and image completion stream, to capture the synchronous and dynamic interplay between structure and texture. Specifically, we first design a structure enhancement module to restore the Histograms of Oriented Gradient (HOG) and the edge of an input image in a sketch space, which forms the input of the structure target stream. Meanwhile, in the image completion stream, we design a channel-space parallel-attention component to facilitate the efficient co-learning of channel and spatial visual cues. To build a bridge between the two streams, we further develop a structure-texture cross-attention module, wherein both structure and texture are synchronously extracted through self-attention, and texture extraction is implemented by dynamically tracking the structure in a cross-attention fashion, enabling the capture of the intricate interaction between structure and texture. Extensive experiments evaluated on three benchmark datasets, including CelebA, Places2, and Paris StreetView, demonstrate that the proposed TSFormer achieves state-of-the-art performance compared to its competitors. The code is available at https://github.com/GZHU-DVL/TSFormer. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
17. Inferring Object Boundaries and Their Roughness with Uncertainty Quantification.
- Author
-
Maboudi Afkham, Babak, Riis, Nicolai André Brogaard, Dong, Yiqiu, and Hansen, Per Christian
- Abstract
This work describes a Bayesian framework for reconstructing the boundaries that represent targeted features in an image, as well as the regularity (i.e., roughness vs. smoothness) of these boundaries. This regularity often carries crucial information in many inverse problem applications, e.g., for identifying malignant tissues in medical imaging. We represent the boundary as a radial function and characterize the regularity of this function by means of its fractional differentiability. We propose a hierarchical Bayesian formulation which, simultaneously, estimates the function and its regularity, and in addition we quantify the uncertainties in the estimates. Numerical results suggest that the proposed method is a reliable approach for estimating and characterizing object boundaries in imaging applications, as illustrated with examples from high-intensity X-ray CT and image inpainting with Gaussian and Laplace additive noise models. We also show that our method can quantify uncertainties for these noise types, various noise levels, and incomplete data scenarios. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
18. Convolutional long short-term memory neural network for groundwater change prediction.
- Author
-
Patra, Sumriti Ranjan and Chu, Hone-Jay
- Subjects
CONVOLUTIONAL neural networks ,ALLUVIAL streams ,ALLUVIAL fans ,WATER supply ,DEEP learning - Abstract
Forecasting groundwater changes is a crucial step towards effective water resource planning and sustainable management. Conventional models still demonstrated insufficient performance when aquifers have high spatio-temporal heterogeneity or inadequate availability of data in simulating groundwater behavior. In this regard, a spatio-temporal groundwater deep learning model is proposed to be applied for monthly groundwater prediction over the entire Choushui River Alluvial Fan in Central Taiwan. The combination of the Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM) known as Convolutional Long Short-Term Memory (CLSTM) Neural Network is proposed and investigated. Result showed that the monthly groundwater simulations from the proposed neural model were better reflective of the original observation data while producing significant improvements in comparison to only the CNN, LSTM as well as classical neural models. The study also explored the performance of the Masked CLSTM model which is designed to handle missing data by reconstructing incomplete spatio-temporal input images, enhancing groundwater forecasting through image inpainting. The findings indicated that the neural architecture can efficiently extract the relevant spatial features from the past incomplete information of hydraulic head observations under various masking scenarios while simultaneously handling the varying temporal dependencies over the entire study region. The proposed model showed strong reliability in reconstructing and simulating the spatial distribution of hydraulic heads for the following month, as evidenced by low RMSE values and high correlation coefficients when compared to observed data. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
19. Deep Learning-Driven Virtual Furniture Replacement Using GANs and Spatial Transformer Networks.
- Author
-
Vijaykumar, Resmy, Ahmad, Muneer, Ismail, Maizatul Akmar, Ahmad, Iftikhar, and Noreen, Neelum
- Subjects
- *
GENERATIVE adversarial networks , *INTERIOR decoration , *IMAGE segmentation , *HOME furnishings , *DEEP learning , *DESIGN services - Abstract
This study proposes a Generative Adversarial Network (GAN)-based method for virtual furniture replacement within indoor scenes. The proposed method addresses the challenge of accurately positioning new furniture in an indoor space by combining image reconstruction with geometric matching through combining spatial transformer networks and GANs. The system leverages deep learning architectures like Mask R-CNN for executing image segmentation and generating masks, and it employs DeepLabv3+, EdgeConnect algorithms, and ST-GAN networks for carrying out virtual furniture replacement. With the proposed system, furniture shoppers can obtain a virtual shopping experience, providing an easier way to understand the aesthetic effects of furniture rearrangement without putting in effort to physically move furniture. The proposed system has practical applications in the furnishing industry and interior design practices, providing a cost-effective and efficient alternative to physical furniture replacement. The results indicate that the proposed method achieves accurate positioning of new furniture in indoor scenes with minimal distortion or displacement. The proposed system is limited to 2D front-view images of furniture and indoor scenes. Future work would involve synthesizing 3D scenes and expanding the system to replace furniture images photographed from different angles. This would enhance the efficiency and practicality of the proposed system for virtual furniture replacement in indoor scenes. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
20. 基于深度学习的图像修复方法研究进展.
- Author
-
陈文祥, 田启川, 廉露, 张晓行, and 王浩吉
- Abstract
Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) more...
- Published
- 2024
- Full Text
- View/download PDF
21. Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation.
- Author
-
Jeong, Soo-Yeon, Bae, Eun-Jeong, Jang, Hyun Soo, Na, SeongJu, and Ihm, Sun-Young
- Subjects
- *
GENERATIVE adversarial networks , *DATA augmentation , *THREE-dimensional imaging , *DEEP learning , *TEETH , *INPAINTING - Abstract
Traditional dental prosthetics require a significant amount of work, labor, and time. To simplify the process, a method to convert teeth scan images, scanned using an intraoral scanner, into 3D images for design was developed. Furthermore, several studies have used deep learning to automate dental prosthetic processes. Tooth images are required to train deep learning models, but they are difficult to use in research because they contain personal patient information. Therefore, we propose a method for generating virtual tooth images using image-to-image translation (pix2pix) and contextual reconstruction fill (CR-Fill). Various virtual images can be generated using pix2pix, and the images are used as training images for CR-Fill to compare the real image with the virtual image to ensure that the teeth are well-shaped and meaningful. The experimental results demonstrate that the images generated by the proposed method are similar to actual images. In addition, only using virtual images as training data did not perform well; however, using both real and virtual images as training data yielded nearly identical results to using only real images as training data. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
22. AI-Assisted Restoration of Yangshao Painted Pottery Using LoRA and Stable Diffusion.
- Author
-
Zhang, Xinyi
- Subjects
- *
STABLE Diffusion , *ARTISTIC style , *PRESERVATION of painting , *DIGITAL preservation , *IMAGE reconstruction , *POTTERY - Abstract
This study is concerned with the restoration of painted pottery images from the Yangshao period. The objective is to enhance the efficiency and accuracy of the restoration process for complex pottery patterns. Conventional restoration techniques encounter difficulties in accurately and efficiently reconstructing intricate designs. To address this issue, the study proposes an AI-assisted restoration workflow that combines Stable Diffusion models (SD) with Low-Rank Adaptation (LoRA) technology. By training a LoRA model on a dataset of typical Yangshao painted pottery patterns and integrating image inpainting techniques, the accuracy and efficiency of the restoration process are enhanced. The results demonstrate that this method provides an effective restoration tool while maintaining consistency with the original artistic style, supporting the digital preservation of cultural heritage. This approach also offers archaeologists flexible restoration options, promoting the broader application and preservation of cultural heritage. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
23. Symmetric Connected U-Net with Multi-Head Self Attention (MHSA) and WGAN for Image Inpainting.
- Author
-
Hou, Yanyang, Ma, Xiaopeng, Zhang, Junjun, and Guo, Chenxian
- Subjects
- *
CONVOLUTIONAL neural networks , *GENERATIVE adversarial networks , *INPAINTING , *ALGORITHMS - Abstract
This study presents a new image inpainting model based on U-Net and incorporating the Wasserstein Generative Adversarial Network (WGAN). The model uses skip connections to connect every encoder block to the corresponding decoder block, resulting in a strictly symmetrical architecture referred to as Symmetric Connected U-Net (SC-Unet). By combining SC-Unet with a GAN, the study aims to reconstruct images more effectively and seamlessly. The traditional discriminators only differentiate the entire image as true or false. In this study, the discriminator calculated the probability of each pixel belonging to the hole and non-hole regions, which provided the generator with more gradient loss information for image inpainting. Additionally, every block of SC-Unet incorporated a Dilated Convolutional Neural Network (DCNN) to increase the receptive field of the convolutional layers. Our model also integrated Multi-Head Self-Attention (MHSA) into selected blocks to enable it to efficiently search the entire image for suitable content to fill the missing areas. This study adopts the publicly available datasets CelebA-HQ and ImageNet for evaluation. Our proposed algorithm demonstrates a 10% improvement in PSNR and a 2.94% improvement in SSIM compared to existing representative image inpainting methods in the experiment. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
24. Enhancing wildfire detection: a novel algorithm for controllable generation of wildfire smoke images.
- Author
-
Yinuo Huo, Qixing Zhang, Chong Wang, Haihui Wang, and Yongming Zhang
- Subjects
GENERATIVE adversarial networks ,OBJECT recognition (Computer vision) ,DEEP learning ,IMAGE databases ,SMOKE - Abstract
Background. The lack of wildfire smoke image data is one of the most important factors hindering the development of image-based wildfire detection. Smoke image generation based on image inpainting techniques is a solution worthy of study. However, it is difficult to generate smoke texture with context consistency in complex backgrounds with current image inpainting methods. Aims. This work aims to provide a wildfire smoke image database for specific scenarios. Methods. We designed an algorithm based on generative adversarial networks (GANs) to generate smoke images. The algorithm includes a multi-scale fusion module to ensure consistency between the generated smoke and backgrounds. Additionally, a local feature-matching mechanism in the discriminator guides the generator to capture real smoke's feature distribution. Key results. We generated 13,400 wildfire smoke images based on forest background images and early fire simulation from the Fire Dynamics Simulator (FDS). Conclusions. A variety of advanced object detection algorithms were trained based on the generated data. The experimental results confirmed that the addition of the generated data to the real datasets can effectively improve model performance. Implications. This study paves a way for generating object datasets to enhance the reliability of watchtower or satellite wildfire monitoring. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
25. Curvature-Dependent Elastic Bending Total Variation Model for Image Inpainting with the SAV Algorithm.
- Author
-
Nan, Caixia, Qiao, Zhonghua, and Zhang, Qian
- Abstract
Image inpainting is pivotal within the realm of image processing, and many efforts have been dedicated to modeling, theory, and numerical analysis in this research area. In this paper, we propose a curvature-dependent elastic bending total variation model for the inpainting problem, in which the elastic bending energy in the phase-field framework introduces geometric information and the total variation term maintains the sharpness of the inpainting edge, referred to as elastic bending-TV model. The energy stability is theoretically proved based on the scalar auxiliary variable method. Additionally, an adaptive time-stepping algorithm is used to further improve the computational efficiency. Numerical experiments illustrate the effectiveness of the proposed model and verify the capability of our model in image inpainting. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
26. Image inpainting based on tensor ring decomposition with generative adversarial network.
- Author
-
Yuan, Jianjun, Wu, Hong, Zhao, Luoming, and Wu, Fujun
- Abstract
Image inpainting is a fundamental task in the field of computer vision. However, there are three major challenges associated with this technique: (1) maintaining neighborhood texture consistency; (2) ensuring the rationality of visual structure; and (3) the limitation of existing inpainting models based on deep neural networks due to a large number of parameters. In order to tackle these challenges, we propose a novel generative adversarial network based on tensor ring decomposition to inpaint images with varying degrees of damage. First, we design a dual-path block that captures features at different scales without significant memory consumption. Every pair of dual-path blocks is incorporated into an enhanced residual module to integrate local and global features. Additionally, we propose the tensor ring layer to compress the convolution, reducing the number of model parameters and computational complexity. We then use a more accurate U-Net based discriminator to optimize the network by minimizing reconstruction loss, adversarial loss, perceptual loss and style loss. Extensive experiments demonstrate that, when compared with other state-of-the-art algorithms, our model shows superior performance in compression. The repaired images also exhibit reasonable texture structure and contextual semantic information. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
27. 生成对抗网络在老照片档案智能化 修复中的应用.
- Author
-
徐辛酉 and 杨晓芳
- Abstract
Copyright of Archives Science Bulletin is the property of Editorial Office of Archives Science Bulletin, Renmin University of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) more...
- Published
- 2024
28. ArtDiff: Integrating IoT and AI to enhance precision in ancient mural restoration
- Author
-
Yuhan Yan, Bowen Chai, and Jiapeng Li
- Subjects
Ancient murals ,Cultural heritage preservation ,Internet of things ,ArtDiff model ,Image inpainting ,Engineering (General). Civil engineering (General) ,TA1-2040 - Abstract
Ancient murals, as invaluable cultural artifacts, have profound historical and cultural significance. However, these murals often face degradation phenomena such as peeling, fading, and cracking, which compromises their preservation. Conventional methodologies for protection and restoration exhibit limitations and do not adequately address multifaceted damage conditions, thus necessitating the integration of advanced technological interventions to enhance restoration effectiveness.This paper delineates a framework for the preservation and restoration of cultural heritage buildings that uses Internet of Things (IoT) technology and Artificial Intelligence (AI). Using real-time environmental and structural health surveillance, in conjunction with security mechanisms, this framework markedly improves precision and efficiency in forecasting and identifying potential risks.Furthermore, in the context of mural restoration, this paper introduces the ArtDiff model. This model amalgamates a modified U-Net for initial crack detection with an edge-guided restoration technique, employing a diffusion model for meticulous restoration. Empirical results substantiate the superiority of the ArtDiff model in crack detection and mural restoration, delivering a greater precision and efficacy relative to existing approaches. Through the implementation of multilevel supervision strategies and an avant-garde model architecture, this study offers a sophisticated mural restoration solution, furnishing novel technological support for the preservation of cultural heritage. more...
- Published
- 2025
- Full Text
- View/download PDF
29. Study on virtual tooth image generation utilizing CF-fill and Pix2pix for data augmentation
- Author
-
Soo-Yeon Jeong, Eun-Jeong Bae, Hyun Soo Jang, SeongJu Na, and Sun-Young Ihm
- Subjects
Data augmentation ,GAN (generative adversarial network) ,Image inpainting ,CR-Fill ,Pix2pix ,Medicine ,Science - Abstract
Abstract Traditional dental prosthetics require a significant amount of work, labor, and time. To simplify the process, a method to convert teeth scan images, scanned using an intraoral scanner, into 3D images for design was developed. Furthermore, several studies have used deep learning to automate dental prosthetic processes. Tooth images are required to train deep learning models, but they are difficult to use in research because they contain personal patient information. Therefore, we propose a method for generating virtual tooth images using image-to-image translation (pix2pix) and contextual reconstruction fill (CR-Fill). Various virtual images can be generated using pix2pix, and the images are used as training images for CR-Fill to compare the real image with the virtual image to ensure that the teeth are well-shaped and meaningful. The experimental results demonstrate that the images generated by the proposed method are similar to actual images. In addition, only using virtual images as training data did not perform well; however, using both real and virtual images as training data yielded nearly identical results to using only real images as training data. more...
- Published
- 2024
- Full Text
- View/download PDF
30. Residual trio feature network for efficient super-resolution
- Author
-
Junfeng Chen, Mao Mao, Azhu Guan, and Altangerel Ayush
- Subjects
Image inpainting ,Image super-resolution ,Re-parameterization ,Electronic computers. Computer science ,QA75.5-76.95 ,Information technology ,T58.5-58.64 - Abstract
Abstract Deep learning-based approaches have demonstrated impressive performance in single-image super-resolution (SISR). Efficient super-resolution compromises the reconstructed image’s quality to have fewer parameters and Flops. Ensured efficiency in image reconstruction and improved reconstruction quality of the model are significant challenges. This paper proposes a trio branch module (TBM) based on structural reparameterization. TBM achieves equivalence transformation through structural reparameterization operations, which use a complex network structure in the training phase and convert it to a more lightweight structure in the inference, achieving efficient inference while maintaining accuracy. Based on the TBM, we further design a lightweight version of the enhanced spatial attention mini (ESA-mini) and the residual trio feature block (RTFB). Moreover, the multiple RTFBs are combined to construct the residual trio network (RTFN). Finally, we introduce a localized contrast loss for better applicability to the super-resolution task, which enhances the reconstruction quality of the super-resolution model. Experiments show that the RTFN framework proposed in this paper outperforms other state-of-the-art efficient super-resolution methods in terms of inference speed and reconstruction quality. more...
- Published
- 2024
- Full Text
- View/download PDF
31. On the long-time behavior of the continuous and discrete solutions of a nonlocal Cahn–Hilliard type inpainting model.
- Author
-
Jiang, Dandan, Azaiez, Mejdi, Miranville, Alain, Xu, Chuanju, and Yao, Hui
- Subjects
- *
INPAINTING , *IMAGE reconstruction , *SIGNAL reconstruction - Abstract
In this paper, we study the analytical and numerical long-time stability of a nonlocal Cahn–Hilliard model with a fidelity term for image inpainting introduced in our previous work (Jiang et al., 2024). First, we establish the uniform boundedness of the continuous problem in both L 2 and H 1 spaces, which is obtained by using the Gagliardo–Nirenberg inequality and the uniform Grönwall lemma. Then, for the temporal semi-discrete scheme, the uniform estimates in L 2 and H 1 spaces are derived with the aid of the discrete uniform Grönwall lemma under a suitable assumption on the nonlinear potential. This demonstrates the long-time stability of the proposed scheme in L 2 and H 1 spaces. Finally, we validate the long-time stability and the applicability of our method in signal reconstruction and image inpainting. These numerical experiments demonstrate the high effectiveness of our proposed model. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
32. WFIL-NET: image inpainting based on wavelet downsampling and frequency integrated learning module: WFIL-NET: image inpainting based on wavelet downsampling...: Y. Cao et al.
- Author
-
Cao, Yu, Ma, Ran, Zhao, KaiFan, and An, Ping
- Abstract
The purpose of image inpainting is to restore and fill missing areas, and how to restore delicate and reasonable missing content has always been one key issue. In the past decade, remarkable achievements have been made in image inpainting based on deep learning. However, when faced with large and irregular missing areas, there are still some problems such as semantic inconsistency, blurred edges and artifacts in the inpainted images. To address these problems, this paper proposes a novel image inpainting algorithm WFIL-NET which is based on wavelet downsampling and frequency integrated learning module. The WFIL-NET adopts the generative adversarial network (GAN) structure, where the Encoder–Decoder network is used in the generator part. To retain rich information while reducing the image resolution, we propose to use wavelet downsampling module in the encoder part to enhance the capacity of subsequent operations to learn representative features. Moreover, the wavelet transform extracts image features at different frequency levels: low-frequency information encapsulates the primary content and structure, whereas high-frequency information captures details and texture. The proposed frequency integrated learning module employs the attention mechanism to allocate appropriate weights to high and low frequency information, effectively integrating them to ensure a more coherent structure and semantic consistency in the inpainted image. Experimental results on the CelebA-HQ and Places2 datasets demonstrate that the proposed method effectively fills large and irregular missing areas, significantly enhances the visual quality of inpainted images, and mitigates edge blurring and artifacts. [ABSTRACT FROM AUTHOR] more...
- Published
- 2025
- Full Text
- View/download PDF
33. Non-convex fractional-order TV model for image inpainting: Non-convex fractional-order TV model for image inpainting: W. Lian et al.
- Author
-
Lian, Wenhui, Liu, Xinwu, and Chen, Yue
- Abstract
This paper aims to address the challenge of effectively processing missing or corrupted image areas using the known image information. In this study, we consider a novel non-convex and non-smooth variational model tailored for image inpainting. Our scheme introduces the non-convex potential function into the fractional-order total variation regularization, which is designed to overcome the limitations of classical total variation and higher-order derivative methods that often result in the undesirable staircase effect and blurred contours. This innovative technique effectively mitigates these issues, significantly improving restoration quality. Numerically, to tackle the constructed optimization problem, we design a practical primal–dual algorithm that integrates with the iteratively reweighted ℓ 1 algorithm. Extensive simulation experiments demonstrate that our method achieves the remarkable improvements of approximately 5% in PSNR, and 3% in both SSIM and FSIM compared to other approaches, conclusively showing its capability to deliver visually realistic inpainting results with superior quantitative metrics. [ABSTRACT FROM AUTHOR] more...
- Published
- 2025
- Full Text
- View/download PDF
34. PRN: progressive reasoning network and its image completion applications
- Author
-
Yongqin Zhang, Xiaoyu Wang, Panpan Zhu, Xuan Lu, Jinsheng Xiao, Wei Zhou, Zhan Li, and Xianlin Peng
- Subjects
Image completion ,Image inpainting ,Deep learning ,Ancient murals ,Pigment shedding ,Medicine ,Science - Abstract
Abstract Ancient murals embody profound historical, cultural, scientific, and artistic values, yet many are afflicted with challenges such as pigment shedding or missing parts. While deep learning-based completion techniques have yielded remarkable results in restoring natural images, their application to damaged murals has been unsatisfactory due to data shifts and limited modeling efficacy. This paper proposes a novel progressive reasoning network designed specifically for mural image completion, inspired by the mural painting process. The proposed network comprises three key modules: a luminance reasoning module, a sketch reasoning module, and a color fusion module. The first two modules are based on the double-codec framework, designed to infer missing areas’ luminance and sketch information. The final module then utilizes a paired-associate learning approach to reconstruct the color image. This network utilizes two parallel, complementary pathways to estimate the luminance and sketch maps of a damaged mural. Subsequently, these two maps are combined to synthesize a complete color image. Experimental results indicate that the proposed network excels in restoring clearer structures and more vivid colors, surpassing current state-of-the-art methods in both quantitative and qualitative assessments for repairing damaged images. Our code and results will be publicly accessible at https://github.com/albestobe/PRN . more...
- Published
- 2024
- Full Text
- View/download PDF
35. Multi‐stage image inpainting using improved partial convolutions
- Author
-
Cheng Li, Dan Xu, and Hao Zhang
- Subjects
image inpainting ,image processing ,image reconstruction ,multi‐step training process ,partial inpainting module ,progressive inpainting module ,Photography ,TR1-1050 ,Computer software ,QA76.75-76.765 - Abstract
Abstract In recent years, deep learning models have dramatically influenced image inpainting. However, many existing studies still suffer from over‐smoothed or blurred textures when missing regions are large or contain rich visual details. To restore textures at a fine‐grained level, a multi‐stage inpainting approach is proposed, which applies a series of partial inpainting modules as well as a progressive inpainting module to inpaint missing areas from their boundaries to the centre successively. Some improvements are made on the partial convolutions to reduce artifacts like blurriness, which require a convolution kernel to contain known pixels more than a certain proportion. Towards photorealistic inpainting results, the intermediate outputs from each stage are used to compute the loss. Finally, to facilitate the training process, a multi‐step training is designed that progressively adds inpainting modules to optimize the model. Experiments show that this method outperforms the current excellent techniques on the publicly available datasets: CelebA, Places2 and Paris StreetView. more...
- Published
- 2024
- Full Text
- View/download PDF
36. MILG: Realistic lip-sync video generation with audio-modulated image inpainting
- Author
-
Han Bao, Xuhong Zhang, Qinying Wang, Kangming Liang, Zonghui Wang, Shouling Ji, and Wenzhi Chen
- Subjects
Lip-sync ,Image inpainting ,Face generation ,Modulated SPD normalization ,Information technology ,T58.5-58.64 - Abstract
Existing lip synchronization (lip-sync) methods generate accurately synchronized mouths and faces in a generated video. However, they still confront the problem of artifacts in regions of non-interest (RONI), e.g., background and other parts of a face, which decreases the overall visual quality. To solve these problems, we innovatively introduce diverse image inpainting to lip-sync generation. We propose Modulated Inpainting Lip-sync GAN (MILG), an audio-constraint inpainting network to predict synchronous mouths. MILG utilizes prior knowledge of RONI and audio sequences to predict lip shape instead of image generation, which can keep the RONI consistent. Specifically, we integrate modulated spatially probabilistic diversity normalization (MSPD Norm) in our inpainting network, which helps the network generate fine-grained diverse mouth movements guided by the continuous audio features. Furthermore, to lower the training overhead, we modify the contrastive loss in lip-sync to support small-batch-size and few-sample training. Extensive experiments demonstrate that our approach outperforms the existing state-of-the-art of image quality and authenticity while keeping lip-sync. more...
- Published
- 2024
- Full Text
- View/download PDF
37. A lightweight image inpainting model for removing unwanted objects from residential real estate's indoor scenes.
- Author
-
Sompoppokasest, Srun and Siriborvornratanakul, Thitirat
- Subjects
GENERATIVE adversarial networks ,RESIDENTIAL real estate ,REAL estate listings ,DEEP learning ,INPAINTING - Abstract
To enhance the appeal of residential real estate listings and captivate online customers, clean and visually convincing indoor scenes are highly desirable. In this research, we introduce an innovative image inpainting model designed to seamlessly replace undesirable elements within images of indoor residential spaces with realistic and coherent alternatives. While Generative Adversarial Networks (GANs) have demonstrated remarkable potential for removing unwanted objects, they can be resource-intensive and face difficulties in consistently producing high-quality outcomes, particularly when unwanted objects are scattered throughout the images. To empower small- and medium-sized businesses with a competitive edge, we present a novel GAN model that is resource-efficient and requires minimal training time using arbitrary mask generation and a novel half-perceptual loss function. Our GAN model achieves compelling results in removing unwanted elements from indoor scenes, demonstrating the capability to train within a single day using a single GPU, all while minimizing the need for extensive post-processing. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
38. Multi‐stage image inpainting using improved partial convolutions.
- Author
-
Li, Cheng, Xu, Dan, and Zhang, Hao
- Subjects
- *
IMAGE reconstruction , *IMAGE processing , *INPAINTING , *DEEP learning , *PIXELS - Abstract
In recent years, deep learning models have dramatically influenced image inpainting. However, many existing studies still suffer from over‐smoothed or blurred textures when missing regions are large or contain rich visual details. To restore textures at a fine‐grained level, a multi‐stage inpainting approach is proposed, which applies a series of partial inpainting modules as well as a progressive inpainting module to inpaint missing areas from their boundaries to the centre successively. Some improvements are made on the partial convolutions to reduce artifacts like blurriness, which require a convolution kernel to contain known pixels more than a certain proportion. Towards photorealistic inpainting results, the intermediate outputs from each stage are used to compute the loss. Finally, to facilitate the training process, a multi‐step training is designed that progressively adds inpainting modules to optimize the model. Experiments show that this method outperforms the current excellent techniques on the publicly available datasets: CelebA, Places2 and Paris StreetView. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
39. Text-free diffusion inpainting using reference images for enhanced visual fidelity.
- Author
-
Kim, Beomjo and Sohn, Kyung-Ah
- Subjects
- *
INPAINTING , *VISUAL education - Abstract
• Language-based Subject Generation faces challenge in accurate portrayal of subject. • Nowadays Reference Guided Generation lacks ability to preserve subject identity. • Exemplar-based instructions with visual tokens preserve visual details of subject. • Model based guidance samples better quality images with different pose. • Our model achieved highest CLIP, DINO score and user study compared to others. This paper presents a novel approach to subject-driven image generation that addresses the limitations of traditional text-to-image diffusion models. Our method generates images using reference images without relying on language-based prompts. We introduce a visual detail preserving module that captures intricate details and textures, addressing overfitting issues associated with limited training samples. The model's performance is further enhanced through a modified classifier-free guidance technique and feature concatenation, enabling the natural positioning and harmonization of subjects within diverse scenes. Quantitative assessments using CLIP, DINO and Quality scores (QS), along with a user study, demonstrate the superior quality of our generated images. Our work highlights the potential of pre-trained models and visual patch embeddings in subject-driven editing, balancing diversity and fidelity in image generation tasks. Our implementation is available at https://github.com/8eomio/Subject-Inpainting. [Display omitted] To create your abstract, type over the instructions in the template box below. Fonts or abstract dimensions should not be changed or altered. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
40. Discrete codebook collaborating with transformer for thangka image inpainting.
- Author
-
Bai, Jinxian, Fan, Yao, and Zhao, Zhiwei
- Subjects
- *
ARTISTIC style , *BUDDHIST art & symbolism , *VECTOR quantization , *FOLK culture , *INPAINTING - Abstract
Thangka, as a precious heritage of painting art, holds irreplaceable research value due to its richness in Tibetan history, religious beliefs, and folk culture. However, it is susceptible to partial damage and form distortion due to natural erosion or inadequate conservation measures. Given the complexity of textures and rich semantics in thangka images, existing image inpainting methods struggle to recover their original artistic style and intricate details. In this paper, we propose a novel approach combining discrete codebook learning with a transformer for image inpainting, tailored specifically for thangka images. In the codebook learning stage, we design an improved network framework based on vector quantization (VQ) codebooks to discretely encode intermediate features of input images, yielding a context-rich discrete codebook. The second phase introduces a parallel transformer module based on a cross-shaped window, which efficiently predicts the index combinations for missing regions under limited computational cost. Furthermore, we devise a multi-scale feature guidance module that progressively fuses features from intact areas with textural features from the codebook, thereby enhancing the preservation of local details in non-damaged regions. We validate the efficacy of our method through qualitative and quantitative experiments on datasets including Celeba-HQ, Places2, and a custom thangka dataset. Experimental results demonstrate that compared to previous methods, our approach successfully reconstructs images with more complete structural information and clearer textural details. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
41. Bridging partial-gated convolution with transformer for smooth-variation image inpainting.
- Author
-
Wang, Zeyu, Shen, Haibin, and Huang, Kejie
- Subjects
INPAINTING ,DEEP learning - Abstract
Deep learning has brought essential improvement to image inpainting technology. Conventional deep-learning methods primarily focus on creating visually appealing content in the missing parts of images. However, these methods usually generate edge variations and blurry structures in the filled images, which lead to imbalances in quantitative metrics PSNR/SSIM and LPIPS/FID. In this work, we introduce a pioneering model called PTG-Fill, which utilizes a coarse-to-fine architecture to achieve smooth-variation image inpainting. Our approach adopts the novel Stable-Partial Convolution to construct the coarse network, which integrates a smooth mask-update process to ensure its long-term operation. Meanwhile, we propose the novel Distinctive-Gated Convolution to construct the refined network, which diminishes pixel-level variations by the distinctive attention. Additionally, we build up a novel Transformer bridger to preserve the in-depth features for image refinement and facilitate the operation of the two-stage network. Our extensive experiments demonstrate that PTG-Fill outperforms previous state-of-the-art methods both quantitatively and qualitatively under various mask ratios on four benchmark datasets: CelebA-HQ, FFHQ, Paris StreetView, and Places2. Code and pre-trained weights are available at https://github.com/zeyuwang-zju/PTG-Fill. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
42. Structure-Guided Image Inpainting Based on Multi-Scale Attention Pyramid Network.
- Author
-
Gong, Jun, Luo, Senlin, Yu, Wenxin, and Nie, Liang
- Subjects
SPARE parts ,FEATURE extraction ,IMAGE processing ,INPAINTING ,STRUCTURAL components - Abstract
Current single-view image inpainting methods often suffer from low image information utilization and suboptimal repair outcomes. To address these challenges, this paper introduces a novel image inpainting framework that leverages a structure-guided multi-scale attention pyramid network. This network consists of a structural repair network and a multi-scale attention pyramid semantic repair network. The structural repair component utilizes a dual-branch U-Net network for robust structure prediction under strong constraints. The predicted structural view then serves as auxiliary information for the semantic repair network. This latter network exploits the pyramid structure to extract multi-scale features of the image, which are further refined through an attention feature fusion module. Additionally, a separable gated convolution strategy is employed during feature extraction to minimize the impact of invalid information from missing areas, thereby enhancing the restoration quality. Experiments conducted on standard datasets such as Paris Street View and CelebA demonstrate the superiority of our approach over existing methods through quantitative and qualitative comparisons. Further ablation studies, by incrementally integrating proposed mechanisms into a baseline model, substantiate the effectiveness of our multi-view restoration strategy, separable gated convolution, and multi-scale attention feature fusion. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
43. Image de-photobombing benchmark.
- Author
-
Patel, Vatsa S., Agrawal, Kunal, Baraheem, Samah S., Yousif, Amira, and Nguyen, Tam V.
- Subjects
DEEP learning ,SIGNAL-to-noise ratio ,INPAINTING ,RESEARCH personnel ,BENCHMARKING (Management) - Abstract
Removing photobombing elements from images is a challenging task that requires sophisticated image inpainting techniques. Despite the availability of various methods, their effectiveness depends on the complexity of the image and the nature of the distracting element. To address this issue, we conducted a benchmark study to evaluate 10 state-of-the-art photobombing removal methods on a dataset of over 300 images. Our study focused on identifying the most effective image inpainting techniques for removing unwanted regions from images. We annotated the photobombed regions that require removal and evaluated the performance of each method using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Fréchet inception distance (FID). The results show that image inpainting techniques can effectively remove photobombing elements, but more robust and accurate methods are needed to handle various image complexities. Our benchmarking study provides a valuable resource for researchers and practitioners to select the most suitable method for their specific photobombing removal task. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
44. Patching‐based deep‐learning model for the inpainting of Bragg coherent diffraction patterns affected by detector gaps.
- Author
-
Masto, Matteo, Favre-Nicolin, Vincent, Leake, Steven, Schülli, Tobias, Richard, Marie-Ingrid, and Bellec, Ewen
- Subjects
- *
DIFFRACTION patterns , *DEEP learning , *INPAINTING , *PREDICTION models , *DETECTORS - Abstract
A deep‐learning algorithm is proposed for the inpainting of Bragg coherent diffraction imaging (BCDI) patterns affected by detector gaps. These regions of missing intensity can compromise the accuracy of reconstruction algorithms, inducing artefacts in the final result. It is thus desirable to restore the intensity in these regions in order to ensure more reliable reconstructions. The key aspect of the method lies in the choice of training the neural network with cropped sections of diffraction data and subsequently patching the predictions generated by the model along the gap, thus completing the full diffraction peak. This approach enables access to a greater amount of experimental data for training and offers the ability to average overlapping sections during patching. As a result, it produces robust and dependable predictions for experimental data arrays of any size. It is shown that the method is able to remove gap‐induced artefacts on the reconstructed objects for both simulated and experimental data, which becomes essential in the case of high‐resolution BCDI experiments. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
45. Generating 3D Digital Twins of Real Indoor Spaces based on Real-World Point Cloud Data.
- Author
-
Wonseop Shin, Jaeseok Yoo, Bumsoo Kim, Yonghoon Jung, Sajjad, Muhammad, Youngsup Park, and Sanghyun Seo
- Abstract
The construction of virtual indoor spaces is crucial for the development of metaverses, virtual production, and other 3D content domains. Traditional methods for creating these spaces are often cost-prohibitive and labor-intensive. To address these challenges, we present a pipeline for generating digital twins of real indoor environments from RGB-D camera-scanned data. Our pipeline synergizes space structure estimation, 3D object detection, and the inpainting of missing areas, utilizing deep learning technologies to automate the creation process. Specifically, we apply deep learning models for object recognition and area inpainting, significantly enhancing the accuracy and efficiency of virtual space construction. Our approach minimizes manual labor and reduces costs, paving the way for the creation of metaverse spaces that closely mimic real-world environments. Experimental results demonstrate the effectiveness of our deep learning applications in overcoming traditional obstacles in digital twin creation, offering high-fidelity digital replicas of indoor spaces. This advancement opens for immersive and realistic virtual content creation, showcasing the potential of deep learning in the field of virtual space construction. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
46. NLKFill: high-resolution image inpainting with a novel large kernel attention.
- Author
-
Wang, Ting, Xiang, Dong, Yang, Chuan, Liang, Jiaying, and Shi, Canghong
- Subjects
CONVOLUTIONAL neural networks ,INPAINTING ,TRANSFORMER models ,DEEP learning - Abstract
The integration of convolutional neural network (CNN) and transformer enhances the network's capacity for concurrent modeling of texture details and global structures. However, training challenges with transformer limit their effectiveness to low-resolution images, leading to increased artifacts in slightly larger images. In this paper, we propose a single-stage network utilizing large kernel attention (LKA) to address high-resolution damaged images. LKA enables the capture of both global and local details, akin to transformer and CNN networks, resulting in high-quality inpainting. Our method excels in: (1) reducing parameters, improving inference speed, and enabling direct training on 1024 × 1024 resolution images; (2) utilizing LKA for enhanced extraction of global high-frequency and local details; (3) demonstrating excellent generalization on irregular mask models and common datasets such as Places2, Celeba-HQ, FFHQ, and the random irregular mask dataset Pconv from NVIDIA. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
47. Context-Encoder-Based Image Inpainting for Ancient Chinese Silk.
- Author
-
Wang, Quan, He, Shanshan, Su, Miao, and Zhao, Feng
- Subjects
IMAGE reconstruction ,SERICULTURE ,DEEP learning ,INPAINTING ,SILK - Abstract
The rapid advancement of deep learning technologies presents novel opportunities for restoring damaged patterns in ancient silk, which is pivotal for the preservation and propagation of ancient silk culture. This study systematically scrutinizes the evolutionary trajectory of image inpainting algorithms, with a particular emphasis on those firmly rooted in the Context-Encoder structure. To achieve this study's objectives, a meticulously curated dataset comprising 6996 samples of ancient Chinese silk (256 × 256 pixels) was employed. Context-Encoder-based image inpainting models—LISK, MADF, and MEDFE—were employed to inpaint damaged patterns. The ensuing restoration effects underwent rigorous evaluation, providing a comprehensive analysis of the inherent strengths and limitations of each model. This study not only provides a theoretical foundation for adopting image restoration algorithms grounded in the Context-Encoder structure but also offers ample scope for exploration in achieving more effective restorations of ancient damaged silk. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
48. Multi-stage few-shot micro-defect detection of patterned OLED panel using defect inpainting and multi-scale Siamese neural network.
- Author
-
Ye, Shujiao, Wang, Zheng, Xiong, Pengbo, Xu, Xinhao, Du, Lintong, Tan, Jiubin, and Wang, Weibo
- Subjects
MACHINE learning ,DEEP learning ,INPAINTING ,ORGANIC light emitting diodes ,ARRAY processing ,POINT defects - Abstract
Automatic micro-defect detection is crucial for promoting efficiency in the production lines of patterned OLED panels. Recently, deep learning algorithms have emerged as promising solutions for micro-defect detection. However, in real-world industrial scenarios, the scarcity of training data or annotations results in a drop in performance. A multi-stage few-shot micro-defect detection approach is proposed for patterned OLED panels to deal with this problem. Firstly, we introduce a converter from defective to defect-free images based on our redesigned Vector Quantized-Variational AutoEncoder (VQ-VAE), aiming to inpaint defects with normal textures. Next, we exploit a region-growing method with automatic seed points to obtain the defect's segmentation and geometric parameters in each image block. Reliable seed points are provided by structural similarity index maps between defective sub-blocks and reconstructed reference. Finally, a multi-scale Siamese neural network is proposed to identify the category of extracted defects. With our proposed approach, detection and classification results of defects can be obtained successively. Our experimental results on samples at different array processes demonstrate the superb adaptability of VQ-VAE, with a defect detection rate ranging from 90.0% to 96.0%. Additionally, compared with existing classification models, our multi-scale Siamese neural network exhibits an impressive 98.6% classification accuracy for a long-tailed defect dataset without overfitting. In summary, the proposed approach shows great potential for practical micro-defect detection in industrial scenarios with limited training data. [ABSTRACT FROM AUTHOR] more...
- Published
- 2024
- Full Text
- View/download PDF
49. 级联式生成对抗网络的全景图像修复.
- Author
-
徐嘉悦, 赵建平, 李冠男, 韩成, 李华, and 徐超
- Subjects
GENERATIVE adversarial networks ,INPAINTING ,ALGORITHMS - Abstract
Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) more...
- Published
- 2024
- Full Text
- View/download PDF
50. Inpainting with style: forcing style coherence to image inpainting with deep image prior
- Author
-
Elena Morotti, Fabio Merizzi, Davide Evangelista, and Pasquale Cascarano
- Subjects
deep learning ,deep image prior ,style transfer ,art restoration ,image inpainting ,unsupervised learning ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
In this paper, we combine the deep image prior (DIP) framework with a style transfer (ST) technique to propose a novel approach (called DIP-ST) for image inpainting of artworks. We specifically tackle cases where the regions to fill in are large. Hence, part of the original painting is irremediably lost, and new content must be generated. In DIP-ST, a convolutional neural network processes the damaged image while a pretrained VGG network forces a style constraint to ensure that the inpainted regions maintain stylistic coherence with the original artwork. We evaluate our method performance to inpaint different artworks, and we compare DIP-ST to some state-of-the-art techniques. Our method provides more reliable solutions characterized by a higher fidelity to the original images, as confirmed by better values of quality assessment metrics. We also investigate the effectiveness of the style loss function in distinguishing between different artistic styles, and the results show that the style loss metric accurately measures artistic similarities and differences. Finally, despite the use of neural networks, DIP-ST does not require a dataset for training, making it particularly suited for art restoration where relevant datasets may be scarce. more...
- Published
- 2024
- Full Text
- View/download PDF
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.