Article
NVIDIA open-sources GATOR, reconstructing complete 3D objects with poses from casual photos, pose accuracy 96.36%
3D视觉工坊 · 微信公众号
NVIDIA and Simon Fraser University propose and open-source GATOR, which reconstructs complete 3D objects aligned with the scene and with poses from casual photos that require no object isolation or calibration, achieving 96.36% ADD-SB@0.1 on HANDAL and 95.63% on ScanNet++.
Part of the event: NVIDIA Open-Sources GATOR: Reconstructing Posed 3D Objects from Casual Photos
This page provides a summary and source link only.