← 研踪 PaperTrailCVF · CVPR 2026:cvf:adeee95fbab5bdf71a336260757f9f44 · 记录 #1
FUN REC * Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
Delitzas, AlexandrosZhang, ChenyangguangGavryushin, AlexeyDi Mario, TommasoSun, BoyangDabral, RishabhGuibas, LeonidasTheobalt, ChristianPollefeys, MarcEngelmann, FrancisBarath, Daniel 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-01 23:04
摘要
We present FunREC, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlike existing methods on articulated reconstruction, which rely on controlled setups, multi-state captures, or CAD priors, FunREC operates directly on in-the-wild human interaction sequences to recover interactable 3D scenes. It automatically discovers articulated parts, estimates their kinematic parameters, tracks their 3D motion, and reconstructs static and moving geometry in canonical space, yielding simulation-compatible meshes. Across new real and simulated benchmarks, FunREC surpasses prior work by a large margin, achieving up to +50 mIoU improvement in part segmentation, 5-10x lower articulation and pose errors, and significantly higher reconstruction accuracy. We further demonstrate applications on URDF/USD export for simulation, hand-guided affordance mapping and robot-scene interaction. Our project page is: functionalscenes.github.io.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
FUN REC * Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
We present FunREC, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlike existing methods on articulated reconstruction, which rely on controlled setups, multi-state captures, or CAD priors, FunREC operates directly on in-the-wild human interaction sequences to recover interactable 3D scenes. It automatically discovers articulated parts, estimates their kinematic parameters, tracks their 3D motion, and reconstructs static and moving geometry in canonical space, yielding simulation-compatible meshes. Across new real and simulated benchmarks, FunREC surpasses prior work by a large margin, achieving up to +50 mIoU improvement in part segmentation, 5-10x lower articulation and pose errors, and significantly higher reconstruction accuracy. We further demonstrate applications on URDF/USD export for simulation, hand-guided affordance mapping and robot-scene interaction. Our project page is: functionalscenes.github.io.
查看此版本解读 →查看此版本原文 ↗