CVPR 2026 Highlight: Pose Graph Optimization Fixes ACE-Zero Drift, Matches COLMAP
zhenjun_zhao · x · 2026-10-28
A CVPR 2026 Highlight paper integrates pose graph optimization into learning-based scene coordinate regression (ACE-Zero). Relative pose constraints are extracted from predicted scene coordinates to build a pose graph, with uncertainty-aware weighting from epipolar and optical-flow consistency to suppress bad refinements. On 7-Scenes the full method averages 21.7 dB PSNR (vs 21.2 for self-reproduced COLMAP, which takes 13h vs 30min), and on Mip-NeRF 360 and Tanks and Temples it matches or exceeds COLMAP.
More from Research
- Rebuilding 'Democracy Does Cause Growth': long-run GDP effect rises to 33.6% with 2024 data — ChenhaoTan · 2026-10-28
- YC-backed Wondersearch claims OpenAI-level retrieval on FiQA with no embeddings, no vector DB — antoine_chaffin · 2026-10-28
- AAAI/ICLR Reviewer: About Half of Reviews Look AI-Generated, Peer Review in Crisis — dsmirza · 2026-10-28
- A bestiary of chaotic attractors from the Field–Golubitsky map, each with Dₙ symmetry — S_Conradi · 2026-10-28
- Manifold AI's WorldScape R²SI Tops RoboDojo Agent Track by Turning Robot Failures Into Skills — jiqizhixin · 2026-10-28
- AXA Uses NVIDIA Earth-2 to Simulate 1,000+ Cyclone Seasons for Storm Risk Modeling — NVIDIAAI · 2026-10-28