MIPI 2024 Challenge on Demosaic for Hybridevs Camera: Methods and Results

Yaqi Wu, Zhihao Fan, Xiaofeng Chu, Jimmy S. Ren, Xiaoming Li, Zongsheng Yue, Chongyi Li, Shangcheng Zhou, Ruicheng Feng, Yuekun Dai, Peiqing Yang, Chen Change Loy, Senyan Xu, Zhijing Sun, Jiaying Zhu, Yurui Zhu, Xueyang Fu, Zheng-Jun Zha, Jun Cao, Cheng Li et al. (29 additional authors not shown)

Abstract: The rising demand for computational photography on mobile devices drives development of advanced image sensors and algorithms for camera systems. But the lack of opportunities for in-depth exchange between industry and academia are constraining the development of Mobile Intelligent Photography and Imaging (MIPI). Building on the successes of the prior MIPI Workshops at ECCV 2022 and CVPR 2023, we are pleased to introduce our third MIPI challenge, which includes three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Demosaic for Hybridevs Camera track on MIPI 2024. A total of 110 participants from both industrial and academic backgrounds contributed many valuable solutions to address the difficulty of the restoration of HybridEVS’s raw data, thus raising the reconstructed performance to a new height. This paper gives a comprehensive description and analysis of all solutions developed during this challenge. More detailed information about this challenge is available at https://mipi-challenge.org/MIPI2024.