-
[pdf]
[arXiv]
[bibtex]@InProceedings{Nah_2021_CVPR, author = {Nah, Seungjun and Son, Sanghyun and Lee, Suyoung and Timofte, Radu and Lee, Kyoung Mu and Chen, Liangyu and Zhang, Jie and Lu, Xin and Chu, Xiaojie and Chen, Chengpeng and Xiong, Zhiwei and Xu, Ruikang and Xiao, Zeyu and Huang, Jie and Zhang, Yueyi and Xi, Si and Wei, Jia and Bai, Haoran and Cheng, Songsheng and Wei, Hao and Sun, Long and Tang, Jinhui and Pan, Jinshan and Lee, Donghyeon and Lee, Chulhee and Kim, Taesung and Wang, Xiaobing and Zhang, Dafeng and Pan, Zhihong and Lin, Tianwei and Wu, Wenhao and He, Dongliang and Li, Baopu and Li, Boyun and Xi, Teng and Zhang, Gang and Liu, Jingtuo and Han, Junyu and Ding, Errui and Tao, Guangpin and Chu, Wenqing and Cao, Yun and Luo, Donghao and Tai, Ying and Lu, Tong and Wang, Chengjie and Li, Jilin and Huang, Feiyue and Chen, Hanting and Chen, Shuaijun and Guo, Tianyu and Wang, Yunhe and Zamir, Syed Waqas and Arora, Aditya and Khan, Salman and Hayat, Munawar and Khan, Fahad Shahbaz and Shao, Ling and Zuo, Yushen and Ou, Yimin and Chai, Yuanjun and Shi, Lei and Liu, Shuai and Lei, Lei and Feng, Chaoyu and Zeng, Kai and Yao, Yuying and Liu, Xinran and Zhang, Zhizhou and Huang, Huacheng and Zhang, Yunchen and Jiang, Mingchao and Zou, Wenbin and Miao, Si and Kim, Yangwoo and Sun, Yuejin and Deng, Senyou and Ren, Wenqi and Cao, Xiaochun and Wang, Tao and Suin, Maitreya and Rajagopalan, A. N. and Van Duong, Vinh and Nguyen, Thuc Huu and Yim, Jonghoon and Jeon, Byeungwoo and Li, Ru and Xie, Junwei and Han, Jong-Wook and Choi, Jun-Ho and Kim, Jun-Hyuk and Lee, Jong-Seok and Zhang, Jiaxin and Peng, Fan and Svitov, David and Pakulich, Dmitry and Kim, Jaeyeob and Jeong, Jechang}, title = {NTIRE 2021 Challenge on Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {149-165} }
NTIRE 2021 Challenge on Image Deblurring
Abstract
Motion blur is a common photography artifact in dynamic environments that typically comes jointly with the other types of degradation. This paper reviews the NTIRE 2021 Challenge on Image Deblurring. In this challenge report, we describe the challenge specifics and the evaluation results from the 2 competition tracks with the proposed solutions. While both the tracks aim to recover a high-quality clean image from a blurry image, different artifacts are jointly involved. In track 1, the blurry images are in a low resolution while track 2 images are compressed in JPEG format. In each competition, there were 338 and 238 registered participants and in the final testing phase, 18 and 17 teams competed. The winning methods demonstrate the state-of-the-art performance on the image deblurring task with the jointly combined artifacts.
Related Material