REACT3D: Recovering Articulations for Interactive Physical 3D Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Zhao, Sun, Boyang, Delitzas, Alexandros, Chen, Jiaqi, Pollefeys, Marc
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914462208884736
author Huang, Zhao
Sun, Boyang
Delitzas, Alexandros
Chen, Jiaqi
Pollefeys, Marc
author_facet Huang, Zhao
Sun, Boyang
Delitzas, Alexandros
Chen, Jiaqi
Pollefeys, Marc
contents Interactive 3D scenes are increasingly vital for embodied intelligence, yet existing datasets remain limited due to the labor-intensive process of annotating part segmentation, kinematic types, and motion trajectories. We present REACT3D, a scalable zero-shot framework that converts static 3D scenes into simulation-ready interactive replicas with consistent geometry, enabling direct use in diverse downstream tasks. Our contributions include: (i) openable-object detection and segmentation to extract candidate movable parts from static scenes, (ii) articulation estimation that infers joint types and motion parameters, (iii) hidden-geometry completion followed by interactive object assembly, and (iv) interactive scene integration in widely supported formats to ensure compatibility with standard simulation platforms. We achieve state-of-the-art performance on detection/segmentation and articulation metrics across diverse indoor scenes, demonstrating the effectiveness of our framework and providing a practical foundation for scalable interactive scene generation, thereby lowering the barrier to large-scale research on articulated scene understanding. Our project page is https://react3d.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2510_11340
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle REACT3D: Recovering Articulations for Interactive Physical 3D Scenes
Huang, Zhao
Sun, Boyang
Delitzas, Alexandros
Chen, Jiaqi
Pollefeys, Marc
Computer Vision and Pattern Recognition
Robotics
Interactive 3D scenes are increasingly vital for embodied intelligence, yet existing datasets remain limited due to the labor-intensive process of annotating part segmentation, kinematic types, and motion trajectories. We present REACT3D, a scalable zero-shot framework that converts static 3D scenes into simulation-ready interactive replicas with consistent geometry, enabling direct use in diverse downstream tasks. Our contributions include: (i) openable-object detection and segmentation to extract candidate movable parts from static scenes, (ii) articulation estimation that infers joint types and motion parameters, (iii) hidden-geometry completion followed by interactive object assembly, and (iv) interactive scene integration in widely supported formats to ensure compatibility with standard simulation platforms. We achieve state-of-the-art performance on detection/segmentation and articulation metrics across diverse indoor scenes, demonstrating the effectiveness of our framework and providing a practical foundation for scalable interactive scene generation, thereby lowering the barrier to large-scale research on articulated scene understanding. Our project page is https://react3d.github.io/
title REACT3D: Recovering Articulations for Interactive Physical 3D Scenes
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2510.11340