arXiv cs.CV
· Papers
StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision
arXiv:2603.29368v2 Announce Type: replace Abstract: Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either Monocular Depth Estimation models or general-purpos