Search

Asphalt aging is the main cause of fatigue failure from asphalt pavements, and it can be divided into thermaloxidative and ultraviolet (UV) aging. In this study, nano-TiO2/Irganox 1010 were added to neat asphalt to simultaneously improve the aging phenomenon of asphalt in a variety of complex conditions of asphalt. We then analyzed and discussed physical properties of nano-TiO2/Irganox 1010 modified asphalt composites. In addition, MSCR (Multiple Stress Creep Recovery) and DSR (Dynamic Shear Rheometer) rheological tests were performed on nano-TiO2/Irganox 1010 modified asphalt with different contents. Aging simulation of nano-TiO2/Irganox 1010 modified asphalt was conducted through the TFOT (The Thin Film Oven Test) and UV test, and microstructure of UV aging was analyzed through scanning electron microscopy. Data analysis showed that the nano-TiO2/Irganox 1010 increased softening point and reduced penetration (25 °C) and ductility (5 °C). The nano-TiO2/Irganox 1010 also improved the creep resistance and rheological properties of the composites. Finally, the analysis of test results under different conditions showed that the addition of nano-TiO2/Irganox 1010 significantly enhanced the ability of asphalt to deal with aging in a variety of complex environments.

The current super‐resolution (SR) deep network is mainly applied to the common image and pays little attention to the image with noise. The remote sensing image contains much noise, so that the SR reconstruction effect is not satisfactory. Therefore, a convolution blind denoising adaptive dense connection SR (CBD‐ADCSR) network for the remote sensing image is proposed in this paper. The whole model is divided into a convolution blind denoising (CBD) network for denoising and an ADCSR network for reconstruction. Firstly, the components of the network are given in detail and are analysed. Secondly, a data set making method is designed combining motion blur, defocusing blur and Gaussian noise, which is used to generate low‐resolution image data sets with complex degradation for the model training. Finally, through the detailed comparative experiment, it is proved that the reconstruction effect of the CBD‐ADCSR model is better than that of the most state‐of‐the‐art algorithms in objective criteria. In addition, compared with the original ADCSR network, CBD‐ADCSR has a stronger ability for noise suppression.

In recent years, to improve the nonlinear feature mapping ability of the image super-resolution network, the depth of the convolutional neural network is getting deeper and deeper. In the existing residual network, the the residual block’s output and input are added directly through the skip connection to deepen the nonlinear mapping layer. However, it can not be proved that every addition is useful to improve the network’s performance. In this paper, based on Dirac convolution, an improved Dirac residual block is proposed, which uses the trainable parameters to adaptively control the balance of the convolution and the skip connection to increase the nonlinear mapping ability of the model. The main body network uses multiple Dirac residual blocks to learn the nonlinear mapping of high-frequency information between LR and HR images. In addition, the global skip connection is realized by sub-pixel convolution, which can learn to use linear mapping of low-frequency features of input LR image. In the training stage, the model uses Adam optimizer for network training and L1 as the loss function. The experiments compare our algorithm with some other state-of-the-art models in PSNR, SSIM, IFC, and visual effect on five different benchmark datasets. The results show that the proposed model has excellent performance both in subjective and objective evaluation.

Asphalt aging is the main cause of fatigue failure of asphalt pavement. The performance of rodlike nano-ZnO is better than that of nano-ZnO in all aspects, and rodlike nanomaterials can red...

Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart. This paper reviews the NTIRE 2021 Challenge on Video Super-Resolution. We present evaluation results from two competition tracks as well as the proposed solutions. Track 1 aims to develop conventional video SR methods focusing on the restoration quality. Track 2 assumes a more challenging environment with lower frame rates, casting spatio-temporal SR problem. In each competition, 247 and 223 participants have registered, respectively. During the final testing phase, 14 teams competed in each track to achieve state-of-the-art performance on video SR tasks.

Increasing model size often results in improved performance on super-resolution reconstruction. However, at some point large model cannot SR huge images due to GPU/TPU memory limitations. In this paper, to address this problem, we present Block-Reconstruction(BR) strategy to improve the reconstruction quality of large images, which lower memory consumption. Meanwhile, we propose an enhanced adaptive dense connection super resolution reconstruction network(EDCSR) that has 89M parameters. In AIM2020 Real Image Super-Resolution Challenge, we won the second place in Track 1 and Track 2, and the third place in Track 3.

This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, ×16, and employs the novel DIVerse 8K resolution (DIV8K) dataset. This report focuses on the proposed solutions and final results. The challenge had 2 tracks. The goal in Track 1 was to generate a super-resolution result with high fidelity, using the conventional PSNR as the primary metric to evaluate different methods. Track 2 instead focused on generating visually more pleasant super-resolution results, evaluated using subjective opinions. The two tracks had 71 and 52 registered participants, respectively, and 9 teams competed in the final testing phase. This report gauges the experimental protocol and baselines for the extreme image super-resolution task.

This paper reviews the AIM 2019 challenge on extreme image super-resolution, the problem of restoring of rich details in a low resolution image. Compared to previous, this challenge focuses on an extreme upscaling factor, x16, and employs the novel DIVerse 8K resolution (DIV8K) dataset. This report focuses on the proposed solutions and final results. The challenge had 2 tracks. The goal in Track 1 was to generate a super-resolution result with high fidelity, using the conventional PSNR as the primary metric to evaluate different methods. Track 2 instead focused on generating visually more pleasant super-resolution results, evaluated using subjective opinions. The two tracks had 71 and 52 registered participants, respectively, and 9 teams competed in the final testing phase. This report gauges the experimental protocol and baselines for the extreme image super-resolution task.