# NVIDIA open-sources GATOR, reconstructing complete 3D objects with poses from casual photos, pose accuracy 96.36%

- Source: 3D视觉工坊 · 微信公众号
- Published: 2026-10-15T23:00:00.000Z
- RoboHot: https://robohot.news/en/items/bd1p41nqjumwpl3aqhn99f5pc
- Original: https://mp.weixin.qq.com/s?__biz=MzU1MjY4MTA1MQ==&mid=2247752192&idx=1&sn=536a67d90dfd2531bfc05e7d8df378be&chksm=fad02a5f9c40ad402af52f22fed3496b8a1876d0ff0c5a59046347c5de94fe1e610aa77d362f&scene=126&sessionid=1792241050#rd

## Summary

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++.