RaCo open-sourced: lightweight keypoint detector trained without covisible pairs
rsasaki0109 · x · 2026-10-12
The GitHub repo for RaCo (136 stars, Apache-2.0) is now public. Authors: Abhiram Shenoi, Philipp Lindenberger, Paul-Edouard Sarlin, Marc Pollefeys; accepted at 3DV 2026.
- Lightweight network learning robust, versatile keypoints for 3D vision tasks
- Three components: repeatable keypoint detector, differentiable ranker to maximize matches with limited keypoints, covariance estimator for metric-scale spatial uncertainty
- Trained only on perspective image crops — no covisible image pairs needed
- Includes demo notebooks, matching demo, and PyTorch Hub support
More from Research
- BudgetPix: adaptive tokenization matches pixel diffusion fidelity with just 25% of the compute — Ozgur Kara · 2026-10-13
- DeepMind's AlphaProof Nexus Paper Published in Science Magazine — swarat · 2026-10-13
- Google published 90 peer-reviewed disease papers in 5 years, 90k+ citations — ymatias · 2026-10-13
- Sakana AI and Berkeley propose MASS: multi-agent self-supervision for recursive self-improvement — TheTuringPost · 2026-10-13
- AI forecasts patient physiology to optimise IV-to-oral antibiotic switching, published in Nature Communications — ai_ucl · 2026-10-13
- 60.6% of LLM theorem rewrites silently drop hidden hypotheses, study finds — MFarajtabar · 2026-10-13