Research map / 3D vision / Depth and stereo
Fundamental Matrix Estimation Using Relative Depths
Yaqing Ding, Václav Vávra, Snehal Bhayani, Qianliang Wu, Jian Yang, Zuzana Kukelova
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 |
|---|---|---|---|
| add accurate relative depths to minimal solvers (4p4d vs 7pt) | fundamental matrix estimation in GC-RANSAC · Phototourism, SIFT+NN | rotation error (deg): 2.58 -> 1.90 | Improved |
| add accurate relative depths (4p4d vs 7pt) | fundamental matrix estimation · ETH3D, SP+LG | rotation error (deg): 1.47 -> 0.68 | Improved |
| add relative depths (4p4d vs 7pt) | fundamental matrix estimation · KITTI, SIFT+NN | rotation error (deg): 0.11 -> 0.09 | No clear effect |
| approximate relative depth from SIFT scales instead of accurate depth (ablation) | 4p4d · Phototourism, SIFT+NN | rotation error (deg): 1.90 -> 2.69 | Hurt |
| use monocular Depth Anything depth instead of accurate depth (ablation) | 4p4d · Phototourism, SIFT+NN | rotation error (deg): 1.90 -> 2.73 | Hurt |
| use depth from SIFT scales with LightGlue matching (ablation) | 4p4d · ETH3D, SIFT+LG | rotation error (deg): 2.36 -> 2.63 | Hurt |
| use equal-focal-length 3p3d solver with relative depth instead of 6pt | equal unknown focal length estimation · Phototourism, SP+LG | run-time (ms): 34.0 -> 23.4 | Improved |
| increase noise in relative depths beyond 0.5% (ablation) | proposed solvers · synthetic data | rotation error | Hurt |
| add equal-focal-length constraint | fundamental matrix estimation · real datasets | accuracy | Improved |
Closest papers by meaning
- Linear Fundamental Matrix Estimation from 7 or 5 Points (CVPR 2026 · similarity 0.89)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors (CVPR 2025 · similarity 0.88)
- RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions (NeurIPS 2024 · similarity 0.85)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.84)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.84)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · 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.
