Removing Foreground Occlusions in Light Field using Micro-lens Dynamic Filter
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1302-1308.
https://doi.org/10.24963/ijcai.2021/180
Keywords
- Computer Vision: Computational Photography, Photometry, Shape from X
- Computer Vision: 2D and 3D Computer Vision
Abstract
Foreground occlusion removal task aims to automatically detect and remove foreground occlusions and recover background objects. Since for Light Fields (LFs), background objects occluded in some views may be seen in other views, the foreground occlusion removal task for LFs is easy to achieve. In this paper, we propose a learning-based method combining ‘seeking’ and ‘generating’ to recover occluded background. Specifically, the micro-lens dynamic filters are proposed to ‘seek’ occluded background points in shifted micro-lens images and remove occlusions using angular information. The shifted images are then combined to further ‘generate’ background regions to supplement more background details using spatial information. By fully exploring the angular and spatial information in LFs, the dense and complex occlusions can be easily removed. Quantitative and qualitative experimental results show that our method outperforms other state-of-the-arts methods by a large margin.
@inproceedings{ijcai2021p180,
title = {Removing Foreground Occlusions in Light Field using Micro-lens Dynamic Filter},
author = {Zhang, Shuo and Shen, Zeqi and Lin, Youfang},
booktitle = {Proceedings of the Thirtieth International Joint Conference on
Artificial Intelligence, {IJCAI-21}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Prof. Zhi-Hua Zhou},
pages = {1302--1308},
year = {2021},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2021/180},
url = {https://doi.org/10.24963/ijcai.2021/180},
}
TY - CPAPER TI - Removing Foreground Occlusions in Light Field using Micro-lens Dynamic Filter AU - Zhang, Shuo AU - Shen, Zeqi AU - Lin, Youfang T2 - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2021 SP - 1302 EP - 1308 DO - 10.24963/ijcai.2021/180 UR - https://doi.org/10.24963/ijcai.2021/180 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: