Search

Your search keyword '"Xu, Ruikang"' showing total 35 results
Start Over Author "Xu, Ruikang"
35 results on '"Xu, Ruikang"'

1. Diffusion-Promoted HDR Video Reconstruction

Author

Guan, Yuanshen, Xu, Ruikang, Yao, Mingde, Gao, Ruisheng, Wang, Lizhi, and Xiong, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

High dynamic range (HDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects such as ghosting artifacts and missing details in saturated regions. In this paper, we propose a diffusion-promoted method for HDR video reconstruction, termed HDR-V-Diff, which incorporates a diffusion model to capture the HDR distribution. As such, HDR-V-Diff can reconstruct HDR videos with realistic details while alleviating ghosting artifacts. However, the direct introduction of video diffusion models would impose massive computational burden. Instead, to alleviate this burden, we first propose an HDR Latent Diffusion Model (HDR-LDM) to learn the distribution prior of single HDR frames. Specifically, HDR-LDM incorporates a tonemapping strategy to compress HDR frames into the latent space and a novel exposure embedding to aggregate the exposure information into the diffusion process. We then propose a Temporal-Consistent Alignment Module (TCAM) to learn the temporal information as a complement for HDR-LDM, which conducts coarse-to-fine feature alignment at different scales among video frames. Finally, we design a Zero-Init Cross-Attention (ZiCA) mechanism to effectively integrate the learned distribution prior and temporal information for generating HDR frames. Extensive experiments validate that HDR-V-Diff achieves state-of-the-art results on several representative datasets., Comment: Arxiv Preprint

Published
2024

3. Neural Degradation Representation Learning for All-In-One Image Restoration

Author

Yao, Mingde, Xu, Ruikang, Guan, Yuanshen, Huang, Jie, and Xiong, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR decomposes different types of degradations adaptively, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively recognize and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalization capability of our method.

Published
2023

4. Generalized Lightness Adaptation with Channel Selective Normalization

Author

Yao, Mingde, Huang, Jie, Jin, Xin, Xu, Ruikang, Zhou, Shenglong, Zhou, Man, and Xiong, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Lightness adaptation is vital to the success of image processing to avoid unexpected visual deterioration, which covers multiple aspects, e.g., low-light image enhancement, image retouching, and inverse tone mapping. Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability. To address this limitation, we propose a novel generalized lightness adaptation algorithm that extends conventional normalization techniques through a channel filtering design, dubbed Channel Selective Normalization (CSNorm). The proposed CSNorm purposely normalizes the statistics of lightness-relevant channels and keeps other channels unchanged, so as to improve feature generalization and discrimination. To optimize CSNorm, we propose an alternating training strategy that effectively identifies lightness-relevant channels. The model equipped with our CSNorm only needs to be trained on one lightness condition and can be well generalized to unknown lightness conditions. Experimental results on multiple benchmark datasets demonstrate the effectiveness of CSNorm in enhancing the generalization ability for the existing lightness adaptation methods. Code is available at https://github.com/mdyao/CSNorm., Comment: Accepted to ICCV 2023. Code: https://github.com/mdyao/CSNorm/

Published
2023

5. Mutual-Guided Dynamic Network for Image Fusion

Author

Guan, Yuanshen, Xu, Ruikang, Yao, Mingde, Wang, Lizhi, and Xiong, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Image fusion aims to generate a high-quality image from multiple images captured under varying conditions. The key problem of this task is to preserve complementary information while filtering out irrelevant information for the fused result. However, existing methods address this problem by leveraging static convolutional neural networks (CNNs), suffering two inherent limitations during feature extraction, i.e., being unable to handle spatial-variant contents and lacking guidance from multiple inputs. In this paper, we propose a novel mutual-guided dynamic network (MGDN) for image fusion, which allows for effective information utilization across different locations and inputs. Specifically, we design a mutual-guided dynamic filter (MGDF) for adaptive feature extraction, composed of a mutual-guided cross-attention (MGCA) module and a dynamic filter predictor, where the former incorporates additional guidance from different inputs and the latter generates spatial-variant kernels for different locations. In addition, we introduce a parallel feature fusion (PFF) module to effectively fuse local and global information of the extracted features. To further reduce the redundancy among the extracted features while simultaneously preserving their shared structural information, we devise a novel loss function that combines the minimization of normalized mutual information (NMI) with an estimated gradient mask. Experimental results on five benchmark datasets demonstrate that our proposed method outperforms existing methods on four image fusion tasks. The code and model are publicly available at: https://github.com/Guanys-dar/MGDN., Comment: ACMMM 2023 accepted

Published
2023

6. Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation

Author

Xu, Ruikang, Yao, Mingde, Chen, Chang, Wang, Lizhi, and Xiong, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Existing methods for spectral reconstruction usually learn a discrete mapping from RGB images to a number of spectral bands. However, this modeling strategy ignores the continuous nature of spectral signature. In this paper, we propose Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a novel continuous spectral representation. To this end, we embrace the concept of implicit function and implement a parameterized embodiment with a neural network. Specifically, we first adopt a backbone network to extract spatial features of RGB inputs. Based on it, we devise Spectral Profile Interpolation (SPI) module and Neural Attention Mapping (NAM) module to enrich deep features, where the spatial-spectral correlation is involved for a better representation. Then, we view the number of sampled spectral bands as the coordinate of continuous implicit function, so as to learn the projection from deep features to spectral intensities. Extensive experiments demonstrate the distinct advantage of NeSR in reconstruction accuracy over baseline methods. Moreover, NeSR extends the flexibility of spectral reconstruction by enabling an arbitrary number of spectral bands as the target output., Comment: Accepted to ECCV Workshop 2022

Published
2021

7. EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration

Author

Xu, Ruikang, Xiao, Zeyu, Huang, Jie, Zhang, Yueyi, and Xiong, Zhiwei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Image deblurring has seen a great improvement with the development of deep neural networks. In practice, however, blurry images often suffer from additional degradations such as downscaling and compression. To address these challenges, we propose an Enhanced Deep Pyramid Network (EDPN) for blurry image restoration from multiple degradations, by fully exploiting the self- and cross-scale similarities in the degraded image.Specifically, we design two pyramid-based modules, i.e., the pyramid progressive transfer (PPT) module and the pyramid self-attention (PSA) module, as the main components of the proposed network. By taking several replicated blurry images as inputs, the PPT module transfers both self- and cross-scale similarity information from the same degraded image in a progressive manner. Then, the PSA module fuses the above transferred features for subsequent restoration using self- and spatial-attention mechanisms. Experimental results demonstrate that our method significantly outperforms existing solutions for blurry image super-resolution and blurry image deblocking. In the NTIRE 2021 Image Deblurring Challenge, EDPN achieves the best PSNR/SSIM/LPIPS scores in Track 1 (Low Resolution) and the best SSIM/LPIPS scores in Track 2 (JPEG Artifacts)., Comment: Accepted at NTIRE Workshop, CVPR 2021. Ruikang and Zeyu contribute equally to this work

Published
2021

8. MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results

Author

Feng, Ruicheng, Li, Chongyi, Zhou, Shangchen, Sun, Wenxiu, Zhu, Qingpeng, Jiang, Jun, Yang, Qingyu, Loy, Chen Change, Gu, Jinwei, Zhu, Yurui, Wang, Xi, Fu, Xueyang, Hu, Xiaowei, Hu, Jinfan, Liu, Xina, Chen, Xiangyu, Dong, Chao, Zhang, Dafeng, Huang, Feiyu, Liu, Shizhuo, Wang, Xiaobing, Jin, Zhezhu, Jiang, Xuhao, Shao, Guangqi, Wang, Xiaotao, Lei, Lei, Zhang, Zhao, Zhao, Suiyi, Zheng, Huan, Gao, Yangcheng, Wei, Yanyan, Ren, Jiahuan, Huang, Tao, Fang, Zhenxuan, Huang, Mengluan, Xu, Junwei, Zhang, Yong, Yang, Yuechi, Shu, Qidi, Yang, Zhiwen, Li, Shaocong, Yao, Mingde, Xu, Ruikang, Guan, Yuanshen, Huang, Jie, Xiong, Zhiwei, Zhu, Hangyan, Liu, Ming, Liu, Shaohui, Zuo, Wangmeng, Jia, Zhuang, Song, Binbin, Song, Ziqi, Mao, Guiting, Hou, Ben, Liu, Zhimou, Ke, Yi, Ouyang, Dengpei, Han, Dekui, Zhang, Jinghao, Zhu, Qi, Zheng, Naishan, Zhao, Feng, Jin, Wu, Conde, Marcos, Nathan, Sabari, Timofte, Radu, Xu, Tianyi, Xu, Jun, Hrishikesh, P. S., Puthussery, Densen, Jiji, C. V., Jiang, Biao, Ding, Yuhan, Li, WanZhang, Feng, Xiaoyue, Chen, Sijing, Zhong, Tianheng, Lu, Jiyang, Chen, Hongming, Fan, Zhentao, Chen, Xiang, Goos, Gerhard, Founding 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, Karlinsky, Leonid, editor, Michaeli, Tomer, editor, and Nishino, Ko, editor

Published
2023
Full Text
View/download PDF

9. MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report

Author

Yang, Qingyu, Yang, Guang, Jiang, Jun, Li, Chongyi, Feng, Ruicheng, Zhou, Shangchen, Sun, Wenxiu, Zhu, Qingpeng, Loy, Chen Change, Gu, Jinwei, Wang, Zhen, Li, Daoyu, Zhang, Yuzhe, Peng, Lintao, Chang, Xuyang, Zhang, Yinuo, Bian, Liheng, Li, Bing, Huang, Jie, Yao, Mingde, Xu, Ruikang, Zhao, Feng, Liu, Xiaohui, Xu, Rongjian, Zhang, Zhilu, Wu, Xiaohe, Wang, Ruohao, Li, Junyi, Zuo, Wangmeng, Jia, Zhuang, Lee, DongJae, Jiang, Ting, Wu, Qi, Jiang, Chengzhi, Han, Mingyan, Li, Xinpeng, Lin, Wenjie, Li, Youwei, Fan, Haoqiang, Liu, Shuaicheng, Goos, Gerhard, Founding 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, Karlinsky, Leonid, editor, Michaeli, Tomer, editor, and Nishino, Ko, editor

Published
2023
Full Text
View/download PDF

10. Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation

Author

Xu, Ruikang, Yao, Mingde, Chen, Chang, Wang, Lizhi, Xiong, Zhiwei, Goos, Gerhard, Founding 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, Karlinsky, Leonid, editor, Michaeli, Tomer, editor, and Nishino, Ko, editor

Published
2023
Full Text
View/download PDF

19. MIPI 2023 Challenge on RGBW Fusion: Methods and Results

Author

Sun, Qianhui, primary, Yang, Qingyu, additional, Li, Chongyi, additional, Zhou, Shangchen, additional, Feng, Ruicheng, additional, Dai, Yuekun, additional, Sun, Wenxiu, additional, Zhu, Qingpeng, additional, Loy, Chen Change, additional, Gu, Jinwei, additional, Yu, Hongyuan, additional, Liu, Yuqing, additional, Yu, Weichen, additional, Ge, Lin, additional, Zhang, Xiaolin, additional, Jia, Qi, additional, Zhang, Heng, additional, Yin, Xuanwu, additional, Zuo, Kunlong, additional, Wu, Qi, additional, Lin, Wenjie, additional, Jiang, Ting, additional, Jiang, Chengzhi, additional, Han, Mingyan, additional, Li, Xinpeng, additional, Luo, Jinting, additional, Yu, Lei, additional, Fan, Haoqiang, additional, Liu, Shuaicheng, additional, Wang, Kunyu, additional, Cao, Chengzhi, additional, Guan, Yuanshen, additional, Xia, Jiyuan, additional, Xu, Ruikang, additional, Yao, Mingde, additional, and Xiong, Zhiwei, additional

Published
2023
Full Text
View/download PDF

21. NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results

Author

Wang, Yingqian, primary, Wang, Longguang, additional, Liang, Zhengyu, additional, Yang, Jungang, additional, Timofte, Radu, additional, Guo, Yulan, additional, Jin, Kai, additional, Wei, Zeqiang, additional, Yang, Angulia, additional, Guo, Sha, additional, Gao, Mingzhi, additional, Zhou, Xiuzhuang, additional, Duong, Vinh Van, additional, Nguyen Huu, Thuc, additional, Yim, Jonghoon, additional, Jeon, Byeungwoo, additional, Liu, Yutong, additional, Cheng, Zhen, additional, Xiao, Zeyu, additional, Xu, Ruikang, additional, Xiong, Zhiwei, additional, Liu, Gaosheng, additional, Jin, Manchang, additional, Yue, Huanjing, additional, Yang, Jingyu, additional, Gao, Chen, additional, Zhang, Shuo, additional, Chang, Song, additional, Lin, Youfang, additional, Chao, Wentao, additional, Wang, Xuechun, additional, Wang, Guanghui, additional, Duan, Fuqing, additional, Xia, Wang, additional, Wang, Yan, additional, Xia, Peiqi, additional, Wang, Shunzhou, additional, Lu, Yao, additional, Cong, Ruixuan, additional, Sheng, Hao, additional, Yang, Da, additional, Chen, Rongshan, additional, Wang, Sizhe, additional, Cui, Zhenglong, additional, Chen, Yilei, additional, Lu, Yongjie, additional, Cai, Dongjun, additional, An, Ping, additional, Salem, Ahmed, additional, Ibrahem, Hatem, additional, Yagoub, Bilel, additional, Kang, Hyun-Soo, additional, Zeng, Zekai, additional, and Wu, Heng, additional

Published
2023
Full Text
View/download PDF

24. Modeling and Analysis of Vibration Characteristics of Complex Boundary Annular Plate Under Thermal Environment.

Author

ZHU Ziyuan, XU Ruikang, and WANG Gang

Subjects
STRUCTURAL plates, KINETIC energy, RAYLEIGH-Ritz method, FINITE element method, DEFORMATIONS (Mechanics)
Abstract

Copyright of Transactions of Nanjing University of Aeronautics & Astronautics is the property of Editorial Department of Journal of Nanjing University of Aeronautics & Astronautics 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.)

Published
2023
Full Text
View/download PDF

25. 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

26. NTIRE 2022 Burst Super-Resolution Challenge

Author

Bhat, Goutam, Danelljan, Martin, Timofte, Radu, Cao, Yizhen, Cao, Yuntian, Chen, Meiya, Chen, Xihao, Cheng, Shen, Dudhane, Akshay, Fan, Haoqiang, Gang, Ruipeng, Gao, Jian, Gu, Yan, Huang, Jie, Huang, Liufeng, Jo, Youngsu, Kang, Sukju, Khan, Salman, Khan, Fahad, Kondo, Yuki, Li, Chenghua, Li, Fangya, Li, Jinjing, Li, Youwei, Li, Zechao, Liu, Chenming, Liu, Shuaicheng, Liu, Zikun, Liu, Zhuoming, Luo, Ziwei, Luo, Zhengxiong, Mehta, Nancy, Murala, Subrahmanyam, Nam, Yoonchan, Nakatani, Chihiro, Ostyakov, Pavel, Pan, Jinshan, Song, Ge, Sun, Jian, Sun, Long, Tang, Jinhui, Ukita, Norimichi, Wen, Zhihong, Wu, Qi, Wu, Xiaohe, Xiao, Zeyu, Xiong, Zhiwei, Xu, Rongjian, Xu, Ruikang, Yan, Youliang, Yang, Jialin, Yang, Wentao, Yang, Zhongbao, Yasue, Fuma, Yao, Mingde, Yu, Lei, Zhang, Cong, Zamir, Syed Waqas, Zhang, Jianxing, Zhang, Shuohao, Zhang, Zhilu, Zheng, Qian, Zhou, Gaofeng, Zhussip, Magauiya, Zou, Xueyi, Zuo, Wangmeng, Bhat, Goutam, Danelljan, Martin, Timofte, Radu, Cao, Yizhen, Cao, Yuntian, Chen, Meiya, Chen, Xihao, Cheng, Shen, Dudhane, Akshay, Fan, Haoqiang, Gang, Ruipeng, Gao, Jian, Gu, Yan, Huang, Jie, Huang, Liufeng, Jo, Youngsu, Kang, Sukju, Khan, Salman, Khan, Fahad, Kondo, Yuki, Li, Chenghua, Li, Fangya, Li, Jinjing, Li, Youwei, Li, Zechao, Liu, Chenming, Liu, Shuaicheng, Liu, Zikun, Liu, Zhuoming, Luo, Ziwei, Luo, Zhengxiong, Mehta, Nancy, Murala, Subrahmanyam, Nam, Yoonchan, Nakatani, Chihiro, Ostyakov, Pavel, Pan, Jinshan, Song, Ge, Sun, Jian, Sun, Long, Tang, Jinhui, Ukita, Norimichi, Wen, Zhihong, Wu, Qi, Wu, Xiaohe, Xiao, Zeyu, Xiong, Zhiwei, Xu, Rongjian, Xu, Ruikang, Yan, Youliang, Yang, Jialin, Yang, Wentao, Yang, Zhongbao, Yasue, Fuma, Yao, Mingde, Yu, Lei, Zhang, Cong, Zamir, Syed Waqas, Zhang, Jianxing, Zhang, Shuohao, Zhang, Zhilu, Zheng, Qian, Zhou, Gaofeng, Zhussip, Magauiya, Zou, Xueyi, and Zuo, Wangmeng

Abstract

Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4x higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task., Funding Agencies|Huawei; Reality Labs; Bending Spoons; MediaTek; OPPO; Oddity; Voyage81; ETH Zurich (Computer Vision Lab); University of Wurzburg (CAIDAS)

Published
2022
Full Text
View/download PDF

27. NTIRE 2022 Burst Super-Resolution Challenge

Author

Bhat, Goutam, primary, Danelljan, Martin, additional, Timofte, Radu, additional, Cao, Yizhen, additional, Cao, Yuntian, additional, Chen, Meiya, additional, Chen, Xihao, additional, Cheng, Shen, additional, Dudhane, Akshay, additional, Fan, Haoqiang, additional, Gang, Ruipeng, additional, Gao, Jian, additional, Gu, Yan, additional, Huang, Jie, additional, Huang, Liufeng, additional, Jo, Youngsu, additional, Kang, Sukju, additional, Khan, Salman, additional, Shahbaz Khan, Fahad, additional, Kondo, Yuki, additional, Li, Chenghua, additional, Li, Fangya, additional, Li, Jinjing, additional, Li, Youwei, additional, Li, Zechao, additional, Liu, Chenming, additional, Liu, Shuaicheng, additional, Liu, Zikun, additional, Liu, Zhuoming, additional, Luo, Ziwei, additional, Luo, Zhengxiong, additional, Mehta, Nancy, additional, Murala, Subrahmanyam, additional, Nam, Yoonchan, additional, Nakatani, Chihiro, additional, Ostyakov, Pavel, additional, Pan, Jinshan, additional, Song, Ge, additional, Sun, Jian, additional, Sun, Long, additional, Tang, Jinhui, additional, Ukita, Norimichi, additional, Wen, Zhihong, additional, Wu, Qi, additional, Wu, Xiaohe, additional, Xiao, Zeyu, additional, Xiong, Zhiwei, additional, Xu, Rongjian, additional, Xu, Ruikang, additional, Yan, Youliang, additional, Yang, Jialin, additional, Yang, Wentao, additional, Yang, Zhongbao, additional, Yasue, Fuma, additional, Yao, Mingde, additional, Yu, Lei, additional, Zhang, Cong, additional, Waqas Zamir, Syed, additional, Zhang, Jianxing, additional, Zhang, Shuohao, additional, Zhang, Zhilu, additional, Zheng, Qian, additional, Zhou, Gaofeng, additional, Zhussip, Magauiya, additional, Zou, Xueyi, additional, and Zuo, Wangmeng, additional

Published
2022
Full Text
View/download PDF

28. NTIRE 2022 Challenge on Night Photography Rendering

Author

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

Published
2022
Full Text
View/download PDF

30. NTIRE 2021 Challenge on Video Super-Resolution

Author

Son, Sanghyun, primary, Lee, Suyoung, additional, Nah, Seungjun, additional, Timofte, Radu, additional, Lee, Kyoung Mu, additional, Chan, Kelvin C. K., additional, Zhou, Shangchen, additional, Xu, Xiangyu, additional, Loy, Chen Change, additional, Jiang, Boyuan, additional, Lin, Chuming, additional, Dong, Yuchun, additional, Luo, Donghao, additional, Chu, Wenqing, additional, Ji, Xiaozhong, additional, Yang, Siqian, additional, Tai, Ying, additional, Wang, Chengjie, additional, Li, Jilin, additional, Huang, Feiyue, additional, Chen, Chengpeng, additional, Chu, Xiaojie, additional, Zhang, Jie, additional, Lu, Xin, additional, Chen, Liangyu, additional, Lin, Jing, additional, Du, Guodong, additional, Hao, Jia, additional, Zou, Xueyi, additional, Zhang, Qi, additional, Jiang, Lielin, additional, Li, Xin, additional, Zheng, He, additional, Liu, Fanglong, additional, He, Dongliang, additional, Li, Fu, additional, Dang, Qingqing, additional, Yi, Peng, additional, Wang, Zhongyuan, additional, Jiang, Kui, additional, Jiang, Junjun, additional, Ma, Jiayi, additional, Chen, Yuxiang, additional, Wang, Yutong, additional, Liu, Ting, additional, Sun, Qichao, additional, Liang, Huanwei, additional, Li, Yiming, additional, Li, Zekun, additional, Ruan, Zhubo, additional, Shang, Fanjie, additional, Guo, Chen, additional, Li, Haining, additional, Luo, Renjun, additional, Shen, Longjie, additional, Zafirouli, Kassiani, additional, Karageorgos, Konstantinos, additional, Konstantoudakis, Konstantinos, additional, Dimou, Anastasios, additional, Daras, Petros, additional, Song, Xiaowei, additional, Zhuo, Xu, additional, Liu, Hanxi, additional, Guo, Mengxi, additional, Li, Junlin, additional, Li, Yu, additional, Zhu, Ye, additional, Wang, Qing, additional, Zhao, Shijie, additional, Sun, Xiaopeng, additional, Zhan, Gen, additional, Xie, Tangxin, additional, Jia, Yu, additional, Lu, Yunhua, additional, Zhang, Wenhao, additional, Sun, Mengdi, additional, Michelini, Pablo Navarrete, additional, Zhang, Xueheng, additional, Jiang, Hao, additional, Chen, Zhiyu, additional, Chen, Li, additional, Xiong, Zhiwei, additional, Xiao, Zeyu, additional, Xu, Ruikang, additional, Cheng, Zhen, additional, Fu, Xueyang, additional, Song, Fenglong, additional, Luo, Zhipeng, additional, Yao, Yuehan, additional, Dutta, Saikat, additional, Shah, Nisarg A., additional, Dipta Das, Sourya, additional, Zhao, Peng, additional, Shi, Yukai, additional, Liu, Hongying, additional, Shang, Fanhua, additional, Liu, Yuanyuan, additional, Chen, Fei, additional, Yu, Fangxu, additional, Gao, Ruisheng, additional, Bai, Yixin, additional, Heo, Jeonghwan, additional, Yue, Shijie, additional, Li, Chenghua, additional, Li, Jinjing, additional, Zheng, Qian, additional, Gang, Ruipeng, additional, Song, Ruixia, additional, Wee, Seungwoo, additional, Jeong, Jechang, additional, Li, Chen, additional, Wen, Geyingjie, additional, Chai, Xinning, additional, and Song, Li, additional

Published
2021
Full Text
View/download PDF

31. NTIRE 2021 Challenge for Defocus Deblurring Using Dual-pixel Images: Methods and Results

Author

Abuolaim, Abdullah, primary, Timofte, Radu, additional, Brown, Michael S., additional, Zhang, Dafeng, additional, Wang, Xiaobing, additional, Zamir, Syed Waqas, additional, Arora, Aditya, additional, Khan, Salman, additional, Hayat, Munawar, additional, Khan, Fahad Shahbaz, additional, Shao, Ling, additional, Liu, Shuai, additional, Lei, Lei, additional, Feng, Chaoyu, additional, Xiong, Zhiwei, additional, Xiao, Zeyu, additional, Xu, Ruikang, additional, Zhu, Yunan, additional, Liu, Dong, additional, Vo, Tu, additional, Miao, Si, additional, Shah, Nisarg A., additional, Liang, Pengwei, additional, Zhong, Zhiwei, additional, Hu, Xingyu, additional, Chen, Yiqun, additional, Li, Chenghua, additional, Bai, Xiaoying, additional, Zhang, Chi, additional, Yao, Yiheng, additional, Gang, Ruipeng, additional, Nathan, Sabari, additional, Ragavendran, Thangavelu, additional, Srinija, Venkatakrishnan, additional, and Srivatsav, Venkatakrishnan, additional

Published
2021
Full Text
View/download PDF

32. NTIRE 2021 Challenge on Image Deblurring

Author

Nah, Seungjun, primary, Son, Sanghyun, additional, Lee, Suyoung, additional, Timofte, Radu, additional, Lee, Kyoung Mu, additional, Chen, Liangyu, additional, Zhang, Jie, additional, Lu, Xin, additional, Chu, Xiaojie, additional, Chen, Chengpeng, additional, Xiong, Zhiwei, additional, Xu, Ruikang, additional, Xiao, Zeyu, additional, Huang, Jie, additional, Zhang, Yueyi, additional, Xi, Si, additional, Wei, Jia, additional, Bai, Haoran, additional, Cheng, Songsheng, additional, Wei, Hao, additional, Sun, Long, additional, Tang, Jinhui, additional, Pan, Jinshan, additional, Lee, Donghyeon, additional, Lee, Chulhee, additional, Kim, Taesung, additional, Wang, Xiaobing, additional, Zhang, Dafeng, additional, Pan, Zhihong, additional, Lin, Tianwei, additional, Wu, Wenhao, additional, He, Dongliang, additional, Li, Baopu, additional, Li, Boyun, additional, Xi, Teng, additional, Zhang, Gang, additional, Liu, Jingtuo, additional, Han, Junyu, additional, Ding, Errui, additional, Tao, Guangpin, additional, Chu, Wenqing, additional, Cao, Yun, additional, Luo, Donghao, additional, Tai, Ying, additional, Lu, Tong, additional, Wang, Chengjie, additional, Li, Jilin, additional, Huang, Feiyue, additional, Chen, Hanting, additional, Chen, Shuaijun, additional, Guo, Tianyu, additional, Wang, Yunhe, additional, Zamir, Syed Waqas, additional, Arora, Aditya, additional, Khan, Salman, additional, Hayat, Munawar, additional, Khan, Fahad Shahbaz, additional, Shao, Ling, additional, Zuo, Yushen, additional, Ou, Yimin, additional, Chai, Yuanjun, additional, Shi, Lei, additional, Liu, Shuai, additional, Lei, Lei, additional, Feng, Chaoyu, additional, Zeng, Kai, additional, Yao, Yuying, additional, Liu, Xinran, additional, Zhang, Zhizhou, additional, Huang, Huacheng, additional, Zhang, Yunchen, additional, Jiang, Mingchao, additional, Zou, Wenbin, additional, Miao, Si, additional, Kim, Yangwoo, additional, Sun, Yuejin, additional, Deng, Senyou, additional, Ren, Wenqi, additional, Cao, Xiaochun, additional, Wang, Tao, additional, Suin, Maitreya, additional, Rajagopalan, A. N., additional, Van Duong, Vinh, additional, Nguyen, Thuc Huu, additional, Yim, Jonghoon, additional, Jeon, Byeungwoo, additional, Li, Ru, additional, Xie, Junwei, additional, Han, Jong-Wook, additional, Choi, Jun-Ho, additional, Kim, Jun-Hyuk, additional, Lee, Jong-Seok, additional, Zhang, Jiaxin, additional, Peng, Fan, additional, Svitov, David, additional, Pakulich, Dmitry, additional, Kim, Jaeyeob, additional, and Jeong, Jechang, additional

Published
2021
Full Text
View/download PDF

35. Neural Degradation Representation Learning for All-In-One Image Restoration.

Author

Yao M, Xu R, Guan Y, Huang J, and Xiong Z

Abstract

Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR adaptively decomposes different types of degradations, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively approximate and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalizability of our method. Code is available at https://github.com/mdyao/NDR-Restore.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results