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.
More from Research
- SC Asia 2027 opens call for papers on supercomputing and AI infra, due Oct 7, 2026 — thoefler · 2026-09-07
- Ex-Google Brain: key algorithmic wins came under 1e20 FLOPs, not scale — _arohan_ · 2026-09-07
- Frontier models double as RL teachers for smaller siblings, argues poster — haider1 · 2026-09-07
- Ex-Google Brain researcher: key algorithmic wins were found under 1e20 FLOPs, then scaled to 1e25 — _arohan_ · 2026-09-07
- GlossoGen paper: LLM agents evolve emergent languages humans can't understand — abenitezburraco · 2026-09-07
- New paper resolves three open problems in online fair division with impossibility results — chaumian · 2026-09-07