All-in-depth via Cross-baseline Light Field Camera
Dingjian Jin, Anke Zhang, Jiamin Wu, Gaochang Wu, Haoqian Wang, Lu Fang
Abstract
Light-field (LF) camera holds great promise for passive/general depth estimation benefited from high angular resolution, yet suffering small baseline for distanced region. While stereo solution with large baseline is superior to handle distant scenarios, the problem of limited angular resolution becomes bothering for near objects. Aiming for all-in-depth solution, we propose a cross-baseline LF camera using a commercial LF camera and a monocular camera, which naturally form a 'stereo camera' enabling compensated baseline for LF camera. The idea is simple yet non-trivial, due to the significant angular resolution gap and baseline gap between LF and stereo cameras.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Learning Light Field Angular Super-Resolution via a Geometry-Aware NetworkJing Jin, Junhui Hou, Hui Yuan, Sam KwongAAAI 2020 · 124 citations
- SeLFVi: Self-supervised Light-Field Video Reconstruction from Stereo VideoPrasan A. Shedligeri, Florian Schiffers, Sushobhan Ghosh, Oliver Cossairt et al.ICCV 2021 · 8 citations
- Light Field Super-resolution via Attention-Guided Fusion of Hybrid LensesJing Jin, Junhui Hou, Jie Chen, Sam Kwong et al.ACM MM 2020 · 33 citations
- Flexible Hybrid Lenses Light Field Super-Resolution using Layered RefinementSong Chang, Youfang Lin, Shuo ZhangACM MM 2022 · 11 citations
- Combining Implicit-Explicit View Correlation for Light Field Semantic SegmentationRuixuan Cong, Da Yang, Rongshan Chen, Sizhe Wang et al.CVPR 2023
