Research map / 3D vision / Depth and stereo
General Planar Motion from a Pair of 3D Correspondences
Juan Carlos Dibene, Zhixiang Min, Enrique Dunn
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 |
|---|---|---|---|
| estimate the motion plane jointly instead of requiring ground plane calibration | 2pt-5dof-3d3d · Synthetic, ground plane calibration error -10 to 10 deg | median orientation/translation error | Improved |
| increase deviation from planar motion (non-planarity) (ablation) | 2pt-5dof-3d3d · Synthetic non-planarity | median orientation error | Hurt |
| use 2-point 3D-3D solver instead of calibrated planar solvers under small non-planarity | 2pt-5dof-3d3d · Synthetic non-planarity (<6 deg) | median orientation error | Improved |
| add depth noise (ablation) | 2pt-5dof-3d3d · Synthetic depth noise | median orientation error | Hurt |
| use 2-point solver instead of 3-point 2D-2D planar solver | 2pt-5dof-3d3d · Synthetic execution time | median execution time (us): 59.6 -> 6.7 | Improved |
| use proposed solver instead of 2pt-3dof-2d3d | 2pt-5dof-3d3d · KITTI odometry (ALL) | median orientation error (deg): 0.175 -> 0.168 | Improved |
| use proposed solver instead of 2pt-3dof-2d3d | 2pt-5dof-3d3d · KITTI odometry (ALL) | median translation error (m): 0.094 -> 0.116 | Hurt |
| use proposed solver instead of Ackermann 1-point solver | 2pt-5dof-3d3d · TUM RGB-D (ALL) | success rate (%): 88.8 -> 98.9 | Improved |
| use proposed solver instead of Ackermann 1-point solver | 2pt-5dof-3d3d · TUM RGB-D (ALL) | median orientation error (deg): 0.358 -> 0.530 | Hurt |
Closest papers by meaning
- Trifocal Relative Pose From Lines at Points (TPAMI 2022 · similarity 0.88)
- Minimal Cases for Computing the Generalized Relative Pose Using Affine Correspondences (ICCV 2021 · similarity 0.87)
- Minimal Solutions for Relative Pose With a Single Affine Correspondence (CVPR 2020 · similarity 0.87)
- Minimal Solvers for Relative Pose Estimation of Multi-Camera Systems using Affine Correspondences (IJCV 2022 · similarity 0.87)
- Planar Structure-from-Motion with Affine Camera Models: Closed-Form Solutions, Ambiguities and Degeneracy Analysis (TPAMI 2016 · similarity 0.87)
- Relative Pose Estimation of Calibrated Cameras with Known SE(3) Invariants (ECCV 2020 · similarity 0.86)
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.
