NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

Abdelhamed, Abdelrahman; Afifi, Mahmoud; Timofte, Radu; Brown, Michael S.; Cao, Yue; Zhang, Zhilu; Zuo, Wangmeng; Zhang, Xiaoling; Liu, Jiye; Chen, Wendong; Wen, Changyuan; Li, Meng; Lv, Shuailin; Zhang, Yunchao; Pan, Zhihong; Li, Baopu; Xi, Teng; Fan, Yanwen; Yu, Xiyu; Zhang, Gang; Liu, Jingtuo; Han, Junyu; Ding, Errui; Yu, Songhyun; Park, Bumjun; Jeong, Jechang; Liu, Shuai; Zong, Ziyao; Nan, Nan; Li, Chenghua; Yang, Zhaoxia; Bao, Long; Wang, Shuangquan; Bai, Dingqun; Lee, Jung Won; Kim, Young-Jung; Rho, Kyeongha; Shin, Chanho; Kim, Sungho; Tang, Pengliang; Zhao, Yiyun; Zhou, Yuqian; Yi, Fan; Huang, Thomas S.; Li, Zhihao; Shah, Nisarg; Liu, Wei; Yan, Qing; Zhao, Yuzhi; Możejko, Marcin; Latkowski, Tomasz; Treszczotko, Lukasz; Michał, Szafraniuk,; Trojanowski, Krzysztof; Wu, Yanhong; Michelini, Pablo Navarrete; Hu, Fengshuo; Lu, Yunhua; Kim, Sujin; Kim, Won-Jin; Lee, Jaayeon; Choi, Jang-Hwan; Zhussip, Magauiya; Khassenov, Azamat; Kim, Jong Hyun; Cho, Hwechul; Kansal, Priya; Nathan, Sabari; Ye, Zhangyu; Lu, Xiwen; Wu, Yaqi; Yang, Jiangxin; Cao, Yanlong; Tang, Siliang; Maggioni, Matteo; Marras, Ioannis; Tanay, Thomas; Slabaugh, Greg; Yan, Youliang; Kang, Myungjoo; Choi, Hyoung Gwon; Song, Kyung Ja; Xu, Shusong; Lu, Xiaomu; Wang, Tingniao; Lei, Chunxia; Liu, Bin; Gupta, Rajat; Kumar, Vineet

doi:10.1109/cvprw50498.2020.00256

Cited by 64 publications

(47 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has been widely studied in the image denoising field. Most participants in the NTIRE 2020 Competition [19] achieved excellent results by applying deep learning. Tian et al [20] proved that deep learning is helpful for image denoising through a large number of experiments.…”

Section: B Single-image Deraining Methodsmentioning

confidence: 99%

ETDNet: An Efficient Transformer Deraining Model

Qin

Yan²,

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Rainy days usually degrade the visual effect of images and videos. At present, most deraining models for single images adopt gradual optimization or elimination to remove rain streaks, but actually with relatively low efficiency in real tasks. An efficient one-stage deraining model, Efficient Transformer Derain Network (ETDNet), is proposed to remove rain streaks in single images efficiently. A new Transformer architecture is designed to provide rich multiple scales and context information, making the model extract features in a coarse-to-fine way. Multiple expansion filters with different expansion rates are embedded to predict the suitable kernel for each pixel of the rainy image in a multi-scale way. A multi-scale Loss Function is introduced to restore features with high-fidelity and detail textures. Experiments on Rain100L, Rain100H, and SPA datasets show that compared with other models, the proposed ETDNet reaches the highest PSNR and SSIM values at the fastest speed.

show abstract

Section: B Single-image Deraining Methodsmentioning

confidence: 99%

ETDNet: An Efficient Transformer Deraining Model

Qin

Yan²,

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For real image denoising, we use training images released by the NTIRE 2020 Real Image Denoising Challenge-Track2: sRGB, which are from the SIDD dataset [46]. These training images come from 160 different scene instances.…”

Section: Experiments and Analysismentioning

confidence: 99%

DRNet: A Deep Neural Network With Multi-Layer Residual Blocks Improves Image Denoising

Zhang

Zhu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Recently, with the broad applications of deep learning technology in image denoising, many deep neural networks based on the residual block (ResBlock) have been proposed to improve the performance. This paper presents DC-ResBlock, a ResBlock with an extra dilated convolution, to replace standard ResBlock for image denoising. Our study shows that the deep neural network with DC-ResBlocks, named DRNet, can achieve a very competitive result. We experiment with other residual blocks by adding Rectified Linear Unit, batch normalization, and Dilated Convolution to the standard ResBlock in several different ways. Ablation study shows that DC-Resblock has the best denoising performance. To evaluate the robustness of proposed DRNet, we make a statistical measure using many different random seeds instead of just a single seed, as used by many previous studies. DRNet performs well in denoising gray and color images with additive white Gaussian noise. Furthermore, because of its good performance on the Smartphone Image Denoising Dataset, DRNet is hopeful to be applied in practical tasks.

show abstract

“…Learning in the Wavelet Domain. Learning in the wavelet domain has the advantage of explicitly dealing with signals in different frequency sub-bands, and it has been applied to some high-level vision and low-level vision problems, such as classification [16], [20]- [22], face aging [23], style transfer [24], image denoising [17], [25], [26], image demoireing [27], image/video compression [28], [29], network compression [30], and super-resolution [18], [31], etc. One of the classical image denoising approach is through image shrinkage [32], where the noisy image is decomposed into low and highfrequency components and then thresholding is applied to the high-frequency coefficients to remove high-frequency noise.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, DWT has also been applied in deep learning-based image denoising. The winner of the NTIRE 2020 Denoising Challenge [17] proposes a multi-level wavelet ResNet for image denoising, where DWT and IDWT are used for downsampling and upsampling. Guo et al [34] propose a deep wavelet super-resolution model to recover the residuals of wavelet coefficients of the low resolution image.…”

Section: Related Workmentioning

confidence: 99%

Wavelet-Based Network For High Dynamic Range Imaging

Dai¹,

Li²,

Cao³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly highfrequency signals. In this work, we propose a novel frequencyguided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequencyguided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequencyguided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multiframe HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-ofthe-art performance.

show abstract

NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

Cited by 64 publications

References 35 publications

ETDNet: An Efficient Transformer Deraining Model

ETDNet: An Efficient Transformer Deraining Model

DRNet: A Deep Neural Network With Multi-Layer Residual Blocks Improves Image Denoising

Wavelet-Based Network For High Dynamic Range Imaging

Contact Info

Product

Resources

About