NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge

Liang, Jie; Timofte, Radu; Yi, Qiaosi; Liu, Shuaizheng; Sun, Lingchen; Wu, Rongyuan; Zhang, Xindong; Zeng, Hui; Zhang, Lei; Huang, Yibin; Liu, Shai; Li, Yongqiang; Feng, Chaoyu; Wang, Xiaotao; Lei, Lei; Chen, Yuxiang; Chen, Xiangyu; Chen, Qiubo; Sun, Fengyu; Cui, Mengying; Chen, Jiaxu; Hu, Zhenyu; Liu, Jingyun; Ma, Wenzhuo; Wang, Ce; Zheng, Hanyou; Sun, Wanjie; Chen, Zhenzhong; Luo, Ziwei; Gustafsson, Fredrik K.; Zhao, Zheng; Sjolund, Jens; Schon, Thomas B.; Dun, Xiong; Ji, Pengzhou; Xing, Yujie; Wang, Xuquan; Wang, Zhanshan; Cheng, Xinbin; Xiao, Jun; He, Chenhang; Wang, Xiuyuan; Liu, Zhi-Song; Miao, Zimeng; Yin, Zhicun; Liu, Ming; Zuo, Wangmeng; Li, Shuai

Jie Liang, Radu Timofte, Qiaosi Yi, Shuaizheng Liu, Lingchen Sun, Rongyuan Wu, Xindong Zhang, Hui Zeng, Lei Zhang, Yibin Huang, Shai Liu, Yongqiang Li, Chaoyu Feng, Xiaotao Wang, Lei Lei, Yuxiang Chen, Xiangyu Chen, Qiubo Chen, Fengyu Sun, Mengying Cui, Jiaxu Chen, Zhenyu Hu, Jingyun Liu, Wenzhuo Ma, Ce Wang, Hanyou Zheng, Wanjie Sun, Zhenzhong Chen, Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjolund, Thomas B. Schon, Xiong Dun, Pengzhou Ji, Yujie Xing, Xuquan Wang, Zhanshan Wang, Xinbin Cheng, Jun Xiao, Chenhang He, Xiuyuan Wang, Zhi-Song Liu, Zimeng Miao, Zhicun Yin, Ming Liu, Wangmeng Zuo, Shuai Li; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 6632-6640

Abstract

In this paper we review the NTIRE 2024 challenge on Restore Any Image Model (RAIM) in the Wild. The RAIM challenge constructed a benchmark for image restoration in the wild including real-world images with/without reference ground truth in various scenarios from real applications. The participants were required to restore the real-captured images from complex and unknown degradation where generative perceptual quality and fidelity are desired in the restoration result. The challenge consisted of two tasks. Task one employed real referenced data pairs where quantitative evaluation is available. Task two used unpaired images and a comprehensive user study was conducted. The challenge attracted more than 200 registrations where 39 of them submitted results with more than 400 submissions. Top-ranked methods improved the state-of-the-art restoration performance and obtained unanimous recognition from all 18 judges. The proposed datasets are available at https://drive.google.com/file/d/1DqbxUoiUqkAIkExu3jZAqoElr_nu1IXb/view?usp=sharing and the homepage of this challenge is at https://codalab.lisn.upsaclay.fr/competitions/17632.

Related Material

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2024_CVPR, author = {Liang, Jie and Timofte, Radu and Yi, Qiaosi and Liu, Shuaizheng and Sun, Lingchen and Wu, Rongyuan and Zhang, Xindong and Zeng, Hui and Zhang, Lei and Huang, Yibin and Liu, Shai and Li, Yongqiang and Feng, Chaoyu and Wang, Xiaotao and Lei, Lei and Chen, Yuxiang and Chen, Xiangyu and Chen, Qiubo and Sun, Fengyu and Cui, Mengying and Chen, Jiaxu and Hu, Zhenyu and Liu, Jingyun and Ma, Wenzhuo and Wang, Ce and Zheng, Hanyou and Sun, Wanjie and Chen, Zhenzhong and Luo, Ziwei and Gustafsson, Fredrik K. and Zhao, Zheng and Sjolund, Jens and Schon, Thomas B. and Dun, Xiong and Ji, Pengzhou and Xing, Yujie and Wang, Xuquan and Wang, Zhanshan and Cheng, Xinbin and Xiao, Jun and He, Chenhang and Wang, Xiuyuan and Liu, Zhi-Song and Miao, Zimeng and Yin, Zhicun and Liu, Ming and Zuo, Wangmeng and Li, Shuai}, title = {NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {6632-6640} }