Research map / 3D vision / Depth and stereo
OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
Changhee Won, Jongbin Ryu, Jongwoo Lim
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 |
|---|---|---|---|
| replace SweepNet+SGM with the end-to-end OmniMVS network | spherical sweeping stereo · OmniThings | MAE: 8.87 -> 2.40 | Improved |
| replace stitched DispNet-CSS with OmniMVS | omnidirectional depth · OmniThings | >3 error: 27.77 -> 15.12 | Improved |
| replace MC-CNN+SGM with OmniMVS | spherical sweeping stereo · OmniThings | >3 error: 47.43 -> 15.12 | Improved |
| fine-tune OmniMVS on OmniHouse | OmniMVS · OmniHouse | MAE: 1.72 -> 1.04 | Improved |
| fine-tune OmniMVS on Sunny | OmniMVS · Sunny | MAE: 1.24 -> 0.79 | Improved |
| fine-tune PSMNet on KITTI | PSMNet · OmniThings | MAE: 7.28 -> 9.09 | Hurt |
| fine-tune DispNet-CSS on KITTI | DispNet-CSS · OmniThings | MAE: 4.06 -> 7.81 | Hurt |
| use fine-tuned OmniMVS-ft instead of OmniMVS | OmniMVS · OmniThings | MAE: 2.40 -> 3.52 | Hurt |
| replace DispNet-CSS with OmniMVS | omnidirectional depth · OmniHouse | MAE: 1.54 -> 1.72 | Hurt |
Later papers that compared with this method
3 later accepted papers report OmniMVS+32 as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- MDP-Omni: Parameter-free Multimodal Depth Prior-based Sampling for Omnidirectional Stereo Matching (ICCV 2025 · better on 4 of 4 shared results)
- MODE: Multi-View Omnidirectional Depth Estimation with 360° Cameras (ECCV 2022 · better on 2 of 2 shared results)
- Real-Time Sphere Sweeping Stereo From Multiview Fisheye Images (CVPR 2021 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- End-to-End Learning for Omnidirectional Stereo Matching With Uncertainty Prior (TPAMI 2020 · similarity 0.98)
- OmniVidar: Omnidirectional Depth Estimation From Multi-Fisheye Images (CVPR 2023 · similarity 0.91)
- MODE: Multi-View Omnidirectional Depth Estimation with 360° Cameras (ECCV 2022 · similarity 0.91)
- HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation (CVPR 2025 · similarity 0.88)
- OmniStereo: Real-time Omnidireactional Depth Estimation with Multiview Fisheye Cameras (CVPR 2025 · similarity 0.88)
- Multi-view Reconstruction via SfM-guided Monocular Depth Estimation (CVPR 2025 · similarity 0.87)
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.
