TUM's DeepBA: 2M-Parameter GNN Achieves Cold-Start Bundle Adjustment
TUM's Daniel Cremers team released DeepBA, a 2.04M-parameter GNN that recovers camera poses from 2D matches across arbitrary views. About 590x smaller than VGGT, it surpasses existing learned SfM methods in cold-start bundle adjustment without requiring initialization.
2026-11-18 ~ 2026-11-18 · 2 related posts
- Deep Bundle Adjustment: 590x smaller than VGGT, initialization-free 3D reconstruction beats COLMAP beyond 15 views — Singularitarian · 2026-11-18
- DeepBA: a 2M-parameter GNN learns bundle adjustment and beats prior learned SfM from a cold start — Singularitarian · 2026-11-18