BLASt3R (ECCV'26): uncalibrated bundle adjustment beats all prior calibrated VSLAM methods
zhenjun_zhao · x · 2026-09-07
BLASt3R, an ECCV'26 paper by Leroy, Revaud et al., is a regularized bundle adjustment framework combining a fast multi-view matcher (MUSt3R/MASt3R-style) with monocular depth priors for initialization and regularization. One unified optimization framework with shared hyperparameters handles both online VSLAM and offline reconstruction of unordered image collections, improving speed-accuracy tradeoffs over traditional, feed-forward and hybrid baselines — and its uncalibrated variant outperforms all previous calibrated VSLAM approaches.
Related event: NAVER Open-Sources BLASt3R for Calibration-Free 3D Reconstruction(2 posts)→
More from Research
- Partial RoPE study: rotating ~10% of dims matches full RoPE convergence with 10x smaller cache — BlancheMinerva · 2026-10-26
- Spotting reward hacking in benchmarks is far harder than you think, says AI2 researcher — soldni · 2026-10-26
- RCT: ChatGPT temporarily boosts consultants' data science skills, gains vanish without it — EricTopol · 2026-10-26
- FocusVLA routes robot camera views by predicted interaction intent across task stages — iscas-cloud · 2026-10-26
- Transformers' biggest audio overhaul: unified AudioProcessor architecture — LysandreJik · 2026-10-26
- Free 195-page primer: The Little Book of Generative AI Foundations — caglar_ee · 2026-10-26