CoDimRecon：基于可变形曲线、曲面和体积的仿真就绪3D场景智能体重建
CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes
浏览论文内容
中文总结 AI 辅助
CoDimRecon提出智能体框架，从多视角RGB重建含刚体、铰接体和可变形物体的仿真就绪3D场景，按维度重建曲线、曲面和体积，并通过行为测试迭代修正，在Replica和ScanNet++上取得竞争精度并支持机器人交互。
中文摘要 AI 辅助
从真实世界观测中重建仿真就绪的3D场景，能够支持机器人、游戏和沉浸式应用，然而现有方法大多假设物体为刚体。这为可变形物体留下了重要空白，因为其仿真就绪的几何形状取决于维度（曲线、曲面或体积），且其行为可能需要超越弹性的模型。我们提出了CoDimRecon，一个智能体框架，能够从多视角RGB观测中重建包含刚体、铰接体和可变形物体的可编辑场景。场景级几何先验确定了尺度和布局，而物体级生成的网格引导智能体获得详细且紧凑的几何形状；铰接刚体被分解为具有显式关节的可移动部件。对于可变形物体，按类别划分的智能体会话将曲线重建为带半径的中心线，将曲面重建为带厚度的流形壳，将体积重建为用于体积网格划分的水密实体。可复用的仿真器技能初始化兼容的物理模型和参数，而智能体引导的行为测试暴露不匹配之处，并触发对运动、几何、数值或材料建模的针对性修订。在评估的Replica和ScanNet++场景上，CoDimRecon在实现有竞争力的组合重建精度的同时，还为杆、壳和实体仿真生成了可变形资产。我们进一步展示了所有三种表示上的机器人交互，包括一个受控的折纸案例，其中行为测试促使了塑性弯曲。
英文摘要
Reconstructing simulation-ready 3D scenes from real-world observations enables robotics, gaming, and immersive applications, yet existing methods largely assume rigid objects. This leaves an important gap for deformables, whose simulation-ready geometry depends on dimensionality (curves, surfaces, or volumes) and whose behavior may require models beyond elasticity. We present CoDimRecon, an agentic framework that reconstructs editable scenes containing rigid, articulated, and deformable objects from multi-view RGB observations. Scene-level geometric priors ground scale and layout, while object-level generated meshes guide the agent toward detailed, compact geometry; articulated rigid objects are decomposed into movable parts with explicit joints. For deformables, category-wise agent sessions reconstruct curves as centerlines with radii, surfaces as manifold shells with thickness, and volumes as watertight solids for volumetric meshing. Reusable simulator skills initialize compatible physical models and parameters, while agent-guided behavioral tests expose mismatches and trigger targeted revisions of motion, geometry, numerics, or material modeling. On evaluated Replica and ScanNet++ scenes, CoDimRecon achieves competitive compositional reconstruction accuracy while additionally producing deformable assets for rod, shell, and solid simulation. We further demonstrate robot interactions across all three representations, including a controlled paper-folding case in which behavioral testing motivates plastic bending.
发表机构
- SIGS, Tsinghua University（清华大学深圳国际研究生院）
- Carnegie Mellon University（卡内基梅隆大学）
- Genesis AI
机构由 AI 辅助整理，请以论文原文为准。
