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.

Original post →

More from Research

Research channel →