{"ID":2856323,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11340","arxiv_id":"2510.11340","title":"REACT3D: Recovering Articulations for Interactive Physical 3D Scenes","abstract":"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/","short_abstract":"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-rea...","url_abs":"https://arxiv.org/abs/2510.11340","url_pdf":"https://arxiv.org/pdf/2510.11340v4","authors":"[\"Zhao Huang\",\"Boyang Sun\",\"Alexandros Delitzas\",\"Jiaqi Chen\",\"Marc Pollefeys\"]","published":"2025-10-13T12:37:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[]","has_code":false}