Mundo：从看见一个地方到模拟那里发生的事

AI 摘要

Hugging Face 博客介绍 Mundo 世界模型：用户拍摄几张房间照片后，Mundo 将其重建为可探索、可编辑、可模拟的 3D 世界。它用 3D 包围盒构建场景代理，由 VLM 智能体通过分析-合成循环修正物体位置，并用 MuJoCo 模拟物理运动、视频模型渲染结果。该工作展示了智能体视觉推理在场景重建与机器人任务模拟中的应用。

正文节选

Mundo goes where he pleases! Take a few photos of a room, and Mundo turns them into a world you can explore and simulate. You can explore the room from any viewpoint, make a drawer slide open and an apple fly out, or have a robot walk in and set a bag on the bed. Mundo renders what happens as a video of that room. Project page · Turn a few views of a place into a world you can explore, edit, and simulate. World models capture the structure, appearance, and dynamics of environments to support rec

发布时间：—

抓取时间：2026-10-23 23:24

来源机构：Hugging Face