Research map / 3D vision / Depth and stereo
Latent RANSAC
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Filter hypotheses using latent-space hash collisions before costly verification | RANSAC · Redwood benchmark | avg. time (sec): $0.40$ vs. $0.21$ | Helped |
| Use latent-space collision filtering and verify only colliding hypotheses | RANSAC · Redwood benchmark | recall | Helped |
| Avoid filtering putative matches before estimation | Latent-RANSAC · Redwood benchmark | recall | Helped |
| Use a stricter overlap threshold, reporting pairs with overlap over 40% rather than 30% | Latent-RANSAC · Redwood benchmark | precision and recall | Helped |
| Apply latent-space collision filtering before verification | RANSAC · 2D homography estimation, Zurich Buildings | runtime | Helped |
| Apply latent-space collision filtering before verification | RANSAC · PnP estimation, Old Hospital | runtime | Helped |
Closest papers by meaning
- CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus (CVPR 2020 · similarity 0.88)
- RANSAC Scoring Done Right (NeurIPS 2026 · similarity 0.87)
- PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus (AAAI 2024 · similarity 0.86)
- Noisy One-point Homographies are Surprisingly Good (CVPR 2024 · similarity 0.84)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.82)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.82)
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.