3D视觉工坊 · 微信公众号·· 29 days agoAI score72
NeurIPS'26 Spotlight paper MoSE3 open-sourced: per-pixel 6DoF rigid-body poses from monocular video
Summary
The NeurIPS'26 Spotlight paper MoSE3 has been open-sourced; it can predict, in a feed-forward manner from in-the-wild monocular RGB video, dense SE(3) motion in the world coordinate frame for each pixel (rotation, translation, and rigid-body grouping).
This page provides a summary and source link only. Read the full article at the source.
Source: 3D视觉工坊 · 微信公众号 · mp.weixin.qq.com