-
[pdf]
[arXiv]
[bibtex]@InProceedings{Dai_2023_CVPR, author = {Dai, Yuekun and Li, Chongyi and Zhou, Shangchen and Feng, Ruicheng and Zhu, Qingpeng and Sun, Qianhui and Sun, Wenxiu and Loy, Chen Change and Gu, Jinwei and Liu, Shuai and Wang, Hao and Feng, Chaoyu and Wang, Luyang and Shao, Guangqi and Zhang, Chenguang and Wang, Xiaotao and Lei, Lei and Zhang, Dafeng and Kong, Xiangyu and Liu, Guanqun and Bai, Mengmeng and Ouyang, Jia and Wang, Xiaobing and Yuan, Jiahui and Li, Xinpeng and Jiang, Chengzhi and Jiang, Ting and Lin, Wenjie and Wu, Qi and Han, Mingyan and Luo, Jinting and Yu, Lei and Fan, Haoqiang and Liu, Shuaicheng and Yan, Bo and Li, Zhuang and Li, Yadong and Wang, Hongbin and Song, Soonyong and Fu, Minghan and Khan, Rayyan Azam and Wu, Fangxiang and Zhang, Zhao and Zhao, Suiyi and Zheng, Huan and Gao, Yangcheng and Wei, Yanyan and Ren, Jiahuan and Wang, Bo and Luo, Yan and Gao, Shuaibo and Wu, Wenhui and Kang, Sicong and Akalwadi, Nikhil and Raichur, Ankit and Patil, Vinod and G, Allabakash and A, Swaroop and Joshi, Amogh and Desai, Chaitra and Tabib, Ramesh Ashok and Patil, Ujwala and Mudenagudi, Uma and Li, Sicheng and Zhu, Ruoxi and Lian, Jiazheng and Xu, Shusong and Liu, Zihao and Nathan, Sabari and Kansal, Priya}, title = {MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {2853-2863} }
MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results
Abstract
Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). With the success of the 1st MIPI Workshop@ECCV 2022, we introduce the second MIPI challenge including four tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2023. In total, 120 participants were successfully registered, and 11 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. A detailed description of all models developed in this challenge is provided in this paper. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2023/.
Related Material