-
[pdf]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Yawei and Zhang, Yulun and Timofte, Radu and Van Gool, Luc and Tu, Zhijun and Du, Kunpeng and Wang, Hailing and Chen, Hanting and Li, Wei and Wang, Xiaofei and Hu, Jie and Wang, Yunhe and Kong, Xiangyu and Wu, Jinlong and Zhang, Dafeng and Zhang, Jianxing and Liu, Shuai and Bai, Furui and Feng, Chaoyu and Wang, Hao and Zhang, Yuqian and Shao, Guangqi and Wang, Xiaotao and Lei, Lei and Xu, Rongjian and Zhang, Zhilu and Chen, Yunjin and Ren, Dongwei and Zuo, Wangmeng and Wu, Qi and Han, Mingyan and Cheng, Shen and Li, Haipeng and Jiang, Ting and Jiang, Chengzhi and Li, Xinpeng and Luo, Jinting and Lin, Wenjie and Yu, Lei and Fan, Haoqiang and Liu, Shuaicheng and Arora, Aditya and Zamir, Syed Waqas and Vazquez-Corral, Javier and Derpanis, Konstantinos G. and Brown, Michael S. and Li, Hao and Zhao, Zhihao and Pan, Jinshan and Dong, Jiangxin and Tang, Jinhui and Yang, Bo and Chen, Jingxiang and Li, Chenghua and Zhang, Xi and Zhang, Zhao and Ren, Jiahuan and Ji, Zhicheng and Miao, Kang and Zhao, Suiyi and Zheng, Huan and Wei, YanYan and Liu, Kangliang and Du, Xiangcheng and Liu, Sijie and Zheng, Yingbin and Wu, Xingjiao and Jin, Cheng and Irny, Rajeev and Koundinya, Sriharsha and Kamath, Vighnesh and Khandelwal, Gaurav and Khowaja, Sunder Ali and Yoon, Jiseok and Lee, Ik Hyun and Chen, Shijie and Zhao, Chengqiang and Yang, Huabin and Zhang, Zhongjian and Huang, Junjia and Zhang, Yanru}, title = {NTIRE 2023 Challenge on Image Denoising: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {1905-1921} }
NTIRE 2023 Challenge on Image Denoising: Methods and Results
Abstract
This paper reviews the NTIRE 2023 challenge on image denoising (sigma = 50) with a focus on the proposed solutions and results. The aim is to obtain a network design capable to produce high-quality results with the best performance measured by PSNR for image denoising. Independent additive white Gaussian noise (AWGN) is assumed and the noise level is 50. The challenge had 225 registered participants, and 16 teams made valid submissions. They gauge the state-of-the-art for image denoising.
Related Material