Research map / Probabilistic and scientific modeling / Variational and generative sampling
MAGSAC++, a Fast, Reliable and Accurate Robust Estimator
Check 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 |
|---|---|---|---|
| Replace MAGSAC sigma-consensus polishing with IRLS marginalization and the new quality score | MAGSAC robust estimation · TUM fundamental matrix | median SGD error (pixels): 3.7 -> 3.5 | Helped |
| Replace MAGSAC sigma-consensus polishing with IRLS marginalization and the new quality score | MAGSAC robust estimation · KITTI fundamental matrix | time (ms): 117 -> 8 | Helped |
| Replace MAGSAC sigma-consensus polishing with IRLS marginalization and the new quality score | MAGSAC robust estimation · Tanks and Temples fundamental matrix | median SGD error (pixels): 4.2 -> 3.9 | Helped |
| Replace MAGSAC sigma-consensus polishing with IRLS marginalization and the new quality score | MAGSAC robust estimation · CPC fundamental matrix | failure rate (%): 7.8 -> 7.8 | Helped |
| Replace MAGSAC sigma-consensus polishing with IRLS marginalization and the new quality score | MAGSAC robust estimation · EVD homography | time (ms): 426 -> 173 | Helped |
| Use Progressive NAPSAC instead of PROSAC sampling | MAGSAC++ robust estimation · six homography and fundamental-matrix datasets | processing time: +1.6 times faster | Helped |
| Relax the P-NAPSAC termination criterion with gamma = 0.1 | P-NAPSAC · six homography and fundamental-matrix datasets | processing time | Helped |
| Increase the relaxed termination parameter beyond gamma = 0.1 | P-NAPSAC · six homography and fundamental-matrix datasets | error and failure rate: 0.8 to 1.0 | Hurt |
| Use local-to-global progressive neighborhoods rather than purely local NAPSAC sampling | RANSAC-like robust estimation · homography and fundamental-matrix datasets | sampling speed | Helped |
| Use MAGSAC++ rather than MAGSAC | robust estimation · KITTI fundamental matrix | median SGD error (pixels): 3.5 -> 3.6 | Mixed |
Closest papers by meaning
- PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus (AAAI 2024 · similarity 0.84)
- Stochastic Localization via Iterative Posterior Sampling (ICML 2024 · similarity 0.82)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.82)
- DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling (AAAI 2024 · similarity 0.82)
- Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World (CVPR 2025 · similarity 0.82)
- MAP Estimation with Denoisers: Convergence Rates and Guarantees (NeurIPS 2025 · similarity 0.81)
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.