arXiv cs.AI· Rundong Luo, Yunong Liu, Di Cao, Matthew Tancik, Shyamal Buch, Colton Stearns, Wenqi Xian·· 13 小时前AI 评分38
SceneRig：从单张图像重建可仿真 3D 场景的智能体系统
SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images
AI 导读
SceneRig 是一个智能体系统，可将单张图像重建为可编辑、可直接用于仿真的 3D 场景。它结合几何、视觉与物理工具，并让智能体在物理模拟器内执行“编辑—验证”循环以获得物理稳定性，在实例分割、物体外观与 3D 摆放上均有提升。该系统生成场景对真实机器人策略结果的预测比基线方法更准确，并能更可靠地回放已录制的操作轨迹而无需调整轨迹。
正文 · 原文
Abstract:Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promising alternative, but visual similarity alone is insufficient: objects must also be recovered, accurately placed, and physically grounded. Existing methods that rely on post-hoc physics settling often misplace objects, producing scenes that look correct but behave poorly under manipulation. We present SceneRig, an agentic system that turns a single image into an editable, simulation-ready scene. SceneRig combines geometric, visual, and physical tools to reconstruct a faithful 3D scene. An agent then performs edit-and-validate loops inside a physics simulator to achieve physical stability. Across diverse inputs, SceneRig improves instance segmentation, object-centric appearance, and 3D placement while keeping the reconstructed scenes physically stable. Furthermore, SceneRig is effective for downstream robotics: its scenes predict real-robot policy outcomes more accurately than the baseline method and more reliably support replay of recorded manipulations without trajectory adaptation.
| Comments: | Accepted at CoRL 2026 Agentic Robotics Workshop. Project page: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.28585 [cs.RO] |
| (or arXiv:2610.28585v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28585 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rundong Luo [view email]
[v1]
Tue, 20 Oct 2026 17:39:42 UTC (42,884 KB)
来源：arXiv cs.AI · arxiv.org