Research map / 3D vision / Depth and stereo
Ray Space Features for Plenoptic Structure-From-Motion
Yingliang Zhang, Peihong Yu, Wei Yang, Yuanxi Ma, Jingyi Yu
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 ray-manifold P-SfM instead of point-ray LF-SfM | P-SfM · Synthetic LF pose, GT R:37 T:163mm, noise 2.0 | rotation error (deg): 1.373 -> 0.763 | Improved |
| use ray-manifold P-SfM instead of PnP | P-SfM · Synthetic LF pose, GT R:37 T:163mm, noise 2.0 | rotation error (deg): 9.692 -> 0.763 | Improved |
| use ray-manifold P-SfM instead of ICP | P-SfM · Synthetic LF pose, GT R:37 T:163mm, noise 2.0 | rotation error (deg): 27.965 -> 0.763 | Improved |
| use ray-manifold P-SfM instead of LF-SfM | P-SfM · Synthetic LF pose, GT R:37 T:163mm, noise 2.0 | relative translation error: 0.037 -> 0.020 | Improved |
| use ray-manifold P-SfM instead of PnP | P-SfM · Synthetic LF pose, GT R:14 T:33mm, noise 1.0 | relative translation error: 0.198 -> 0.076 | Improved |
| use ray-manifold P-SfM instead of LF-SfM | P-SfM · Synthetic LF pose, GT R:14 T:33mm, noise 2.0 | rotation error (deg): 0.174 -> 0.808 | Hurt |
| use ray-manifold P-SfM instead of LF-SfM | P-SfM · Synthetic LF pose, GT R:14 T:33mm, noise 0.2 | rotation error (deg): 0.372 -> 0.326 | No clear effect |
| use ray-manifold P-SfM instead of LF-SfM | P-SfM · Synthetic LF pose, GT R:14 T:33mm, noise 1.0 | relative translation error: 0.096 -> 0.076 | Improved |
Closest papers by meaning
- Ray-Space Epipolar Geometry for Light Field Cameras (TPAMI 2020 · similarity 0.88)
- Structure-from-motion in micro-image domain for uncalibrated plenoptic 2.0 cameras (IJCV 2026 · similarity 0.88)
- 3D Scene Flow from 4D Light Field Gradients (ECCV 2018 · similarity 0.86)
- Structure from Motion on a Sphere (ECCV 2016 · similarity 0.86)
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.86)
- CRAYM: Neural Field Optimization via Camera RAY Matching (NeurIPS 2024 · similarity 0.85)
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.
