Research map / 3D vision / Depth and stereo
OmniVidar: Omnidirectional Depth Estimation From Multi-Fisheye Images
Sheng Xie, Daochuan Wang, Yun-Hui Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use OmniVidar instead of OmniMVS-ft | OmniVidar · Meuleman et al. dataset | bad 1.0: 60.372 -> 18.499 | Improved |
| use OmniVidar instead of OmniMVS-ft | OmniVidar · Omnihouse | bad 1.0: 26.357 -> 4.886 | Improved |
| use OmniVidar instead of OmniMVS-ft | OmniVidar · OmniThings | bad 1.0: 59.753 -> 11.199 | Improved |
| use OmniVidar instead of OmniMVS-ft | OmniVidar · Omnihouse | RMSE: 0.929 -> 1.002 | Hurt |
| use OmniVidar instead of OmniMVS-ft | OmniVidar · Omnihouse | MAE: 0.705 -> 1.042 | Hurt |
| use OmniVidar instead of OmniMVS-ft | OmniVidar · OmniVidar runtime evaluation | runtime: 110 ms -> 66 ms | Improved |
| use OmniVidar instead of OmniMVS-ft | OmniVidar · OmniVidar runtime evaluation | memory: 6.8 GB -> 3.7 GB | Improved |
| add a third refracting sphere to the camera model (ablation) | TSCM · 250° FoV calibration | mean reprojection error: 0.1365 px -> 0.1255 px | Improved |
| add a fourth refracting sphere to the camera model (ablation) | TSCM · 220° FoV calibration | mean reprojection error: 0.1970 px -> 0.1952 px | Improved |
| add a fourth refracting sphere to the camera model (ablation) | TSCM · 195° FoV calibration | mean reprojection error: 0.1528 px -> 0.1528 px | No clear effect |
| use epipolar rectification rather than original distorted fisheye images (ablation) | OmniVidar · real-scene depth estimation | depth consistency | Improved |
Closest papers by meaning
- OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching (ICCV 2019 · similarity 0.91)
- OmniStereo: Real-time Omnidireactional Depth Estimation with Multiview Fisheye Cameras (CVPR 2025 · similarity 0.90)
- End-to-End Learning for Omnidirectional Stereo Matching With Uncertainty Prior (TPAMI 2020 · similarity 0.90)
- HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation (CVPR 2025 · similarity 0.87)
- OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos (CVPR 2024 · similarity 0.84)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
