Deep Bundle Adjustment: 590x smaller than VGGT, initialization-free 3D reconstruction beats COLMAP beyond 15 views
Singularitarian · x · 2026-11-18
Daniel Cremers' TUM group (with Munich Center ML) present Deep Bundle Adjustment: accurate and fast 3D reconstruction without initialization. The model is 590x smaller than VGGT while scoring 97.4 vs 99.3 RRA@15 on CO3Dv2, and is faster than COLMAP/GLOMAP beyond 15 views.
More from Research
- Google/Penn State paper: Self-Improvement Memory lifts harness optimization gains by 2.36 points across models — rohanpaul_ai · 2026-11-18
- Google paper: Self-Improvement Memory lifts cross-model harness transfer from 68.41 to 84.75 — rohanpaul_ai · 2026-11-18
- Argon open-sources Alloy, a multi-material physics engine for robot learning on one GPU — ycombinator · 2026-11-18
- Mohit Bansal's distinguished lectures at Columbia and Northwestern on trustworthy agents — mohitban47 · 2026-11-18
- Arc Institute's antiGen and Germinal Multi forecast virus mutations for proactive vaccine design — BrianHie · 2026-11-18
- Zyphra scales subquadratic attention ZHA to trillion-param open models with 9-60x long-context speedups — realmrfakename · 2026-11-18