GRF-Recon: Global Ray-Field Optimization Tackles Long-Sequence 3D Reconstruction
zhenjun_zhao · x · 2026-09-19
GRF-Recon (arXiv:2609.20012) presents a unified framework for stable, scalable feed-forward 3D reconstruction from long monocular sequences. It distills geometric priors into the feed-forward backbone via LoRA adaptation, uses hybrid-weight sparse ray-field optimization for cross-frame consistency, and applies trajectory stitching with joint ray-error optimization to cut accumulated drift — outperforming prior chunk-based approaches.
More from Research
- Resolution-Inspired Pretraining Experiments 'Pretty Much a Disaster,' Researcher Says — gordic_aleksa · 2026-09-19
- Auto-Formalizing a 76-Page Paper With Opus 5 High Would Take ~40 Days — kfountou · 2026-09-19
- ICLR Submissions Near 45,000 as Researcher Decries AI-Generated Paper Slop — DimitrisPapail · 2026-09-19
- Quanta video explains why Navier-Stokes is so hard and how an OpenAI proof could resolve it — eigensteve · 2026-09-19
- BBFM conjectures see formalization progress building on Axiom Math's prior work — ctjlewis · 2026-09-19
- Blog argues pretraining data, not verifiability, makes LLMs good at math and coding — _arohan_ · 2026-09-19