从静止状态观察重建铰接物体

AI 摘要

本文提出了一种从静止状态重建铰接物体的框架，该框架通过融合视觉-语言模型的输出生成一致的部分网格，并利用几何一致性验证合成的运动假设。该方法仅需单个闭合配置即可重建铰接物体，无需观察多个运动状态，在部分分解和物理合理的铰接方面表现出色，与基于运动观察的基线方法性能相当。

正文节选

Articulated Object Reconstruction from Rest-State Observation Abstract A rest-state framework reconstructs articulated objects from a single closed configuration by fusing vision-language outputs into consistent part meshes and validating synthesized motion hypotheses via geometric consistency. Building interactive digital twins requires recovering both 3D geometry and the kinematic structures that govern how objects articulate. Yet existing methods for articulated object reconstruction require

发布时间：—

抓取时间：2026-08-12 14:22

来源机构：Hugging Face