AI RESEARCH
GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss
arXiv CS.CV
•
ArXi:2601.16885v3 Announce Type: replace Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise in camera pose estimation and 3D reconstruction. However, these models typically rely on ground truth labels for