SOURCE-LINKED INTELLIGENCE

GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Feed-forward 3D reconstruction provides an efficient paradigm for scene modeling from image sequences. Scaling these models to large monocular scenarios are constrained by excessive GPU memory footprint, degraded local geometry, and long-term trajectory drift. Existing chunk-based optimization strategies provide limited geometric constraints and fail to maintain global consistency over extended trajectories. We present a unified framework for stable and scalable feed-forward 3D reconstruction from long monocular sequences. Our approach builds on coarse-to-fine trajectory alignment augmented by

Read original source ↗ Open in workspace

recordType

paper

region

Global