LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

Sheng, Hao; Liu, Yebin; Yu, Jingyi; Wu, Gaochang; Xiong, Wei; Cong, Ruixuan; Chen, Rongshan; Guo, Longzhao; Xie, Yanlin; Zhang, Shuo; Chang, Song; Lin, Youfang; Chao, Wentao; Wang, Xuechun; Wang, Guanghui; Duan, Fuqing; Wang, Tun; Yang, Da; Cui, Zhenglong; Wang, Sizhe; Zhao, Mingyuan; Wang, Qiong; Chen, Qianyu; Liang, Zhengyu; Wang, Yingqian; Yang, Jungang; Yang, Xueting; Deng, Junli

Hao Sheng, Yebin Liu, Jingyi Yu, Gaochang Wu, Wei Xiong, Ruixuan Cong, Rongshan Chen, Longzhao Guo, Yanlin Xie, Shuo Zhang, Song Chang, Youfang Lin, Wentao Chao, Xuechun Wang, Guanghui Wang, Fuqing Duan, Tun Wang, Da Yang, Zhenglong Cui, Sizhe Wang, Mingyuan Zhao, Qiong Wang, Qianyu Chen, Zhengyu Liang, Yingqian Wang, Jungang Yang, Xueting Yang, Junli Deng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 3473-3485

Abstract

This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.

Related Material

[pdf]

[bibtex]

@InProceedings{Sheng_2023_CVPR, author = {Sheng, Hao and Liu, Yebin and Yu, Jingyi and Wu, Gaochang and Xiong, Wei and Cong, Ruixuan and Chen, Rongshan and Guo, Longzhao and Xie, Yanlin and Zhang, Shuo and Chang, Song and Lin, Youfang and Chao, Wentao and Wang, Xuechun and Wang, Guanghui and Duan, Fuqing and Wang, Tun and Yang, Da and Cui, Zhenglong and Wang, Sizhe and Zhao, Mingyuan and Wang, Qiong and Chen, Qianyu and Liang, Zhengyu and Wang, Yingqian and Yang, Jungang and Yang, Xueting and Deng, Junli}, title = {LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {3473-3485} }