DS-SAC proposes a deterministic geometric estimator that beats RANSAC on AUC
ducha_aiki · x · 2026-07-25
DS-SAC (Density Search for Sample Consensus) proposes a deterministic alternative to RANSAC-style geometric estimation.
- The method combines trimmed least squares with tree search and several heuristics.
- The paper provides two algorithms: a high-level recursive search procedure and a forward-search routine that alternates between percentile-based point selection and inlier optimization.
- On essential matrix estimation, DS-SAC reports better AUC scores than RANSAC, MAGSAC, LO-RANSAC, and GC-RANSAC, while also being faster in the reported table.
Related event: DS-SAC Introduces Deterministic Geometric Estimation to Challenge RANSAC(2 posts)→
More from Research
- Manifold Muon offers a loss-free path for training MoE routers — tokenbender · 2026-07-25
- Practical multi-agent orchestration for Codex splits work into scout, worker, and coordinator roles — pvncher · 2026-07-25
- MOJO preprint mixes supervised and self-supervised losses for neural foundation models — hugo_larochelle · 2026-07-25
- AI can scan more code than humans, but engineers still own quality — ingliguori · 2026-07-25
- NVIDIA reposts a GPT-like motion model that reproduces clips with 99.98% success — Syntetisaattori · 2026-07-25
- A new AGI essay argues the field is climbing the same mountain from two slopes — op7418 · 2026-07-25