AI RESEARCH
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
arXiv CS.CV
•
ArXi:2605.15828v1 Announce Type: new Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such as depth estimation, camera pose prediction, and point cloud reconstruction in a single forward pass. They have been widely adopted in 3D vision applications, but their billion-scale parameters bring substantial memory and computation overhead, posing challenges for on-device deployment. Post-