Research map / 3D vision / Depth and stereo
Efficient Large Scale Inlier Voting for Geometric Vision Problems
Dror Aiger, Simon Lynen, Jan Hosang, Bernhard Zeisl
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 generalized voting instead of GOPAC branch and bound | GOPAC · Data61/2D3D Scene 1 (11 queries, median) | runtime (s): 457 -> 27 | Improved |
| use generalized voting instead of GOPAC branch and bound | GOPAC · Data61/2D3D Scene 1 (11 queries, median) | pose success rate: 0.82 -> 0.82 | No clear effect |
| use generalized voting instead of GOPAC | GOPAC · Data61/2D3D Scene 1 (11 queries, median) | rotation error (deg): 2.18 -> 0.46 | Improved |
| use generalized voting instead of GOPAC | GOPAC · Data61/2D3D Scene 1 (11 queries, median) | translation error (m): 2.76 -> 2.89 | Hurt |
| use generalized voting instead of RANSAC | RANSAC · Data61/2D3D Scene 1 (11 queries, median) | pose success rate: 0.09 -> 0.82 | Improved |
| use generalized voting instead of GOPAC | GOPAC · Stanford 2D-3D-S Area 3 (CPU, 8 threads) | runtime (s): 508 -> 421 | Improved |
| use generalized voting instead of GOPAC | GOPAC · Stanford 2D-3D-S Area 3 (CPU, 8 threads) | success rate within 60s: 0.19 -> 0.42 | Improved |
| use generalized voting instead of GOPAC | GOPAC · Stanford 2D-3D-S Area 3 (CPU, 8 threads) | pose success rate: 0.77 -> 0.77 | No clear effect |
| use generalized voting instead of GOPAC | GOPAC · Stanford 2D-3D-S Area 3 (CPU, 8 threads) | translation error (m): 0.29 -> 0.38 | Hurt |
| use generalized voting instead of GOPAC | GOPAC · Stanford 2D-3D-S Area 3 (CPU, 8 threads) | rotation error (deg): 3.46 -> 2.81 | Improved |
Closest papers by meaning
- Guaranteed Outlier Removal With Mixed Integer Linear Programs (CVPR 2016 · similarity 0.90)
- Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation (TPAMI 2018 · similarity 0.89)
- Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence (ICCV 2017 · similarity 0.88)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.85)
- Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World (CVPR 2025 · similarity 0.85)
- Learning to Filter Outlier Edges in Global SfM (CVPR 2025 · 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.
