从RGB-D序列联合重建带关节的物理可模拟模型，解决形状与运动参数分离及能量不守恒问题。
URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification
- 通过可微分关节求解器和能量一致性验证，联合优化部件形状、关节拓扑与参数。
- 关节轴误差降低至2.83度，50秒仿真漂移减少64%，操作成功率提升14.6个百分点。
- 适合需要高保真物理模拟的机器人抓取与场景重建任务，尤其关注动态一致性。
从传感器观测中重建可用于仿真的刚性物体数字孪生仍受两大瓶颈制约：(i) 部件几何重建与运动参数估计相互脱节；(ii) 复原模型常违反基本动力学守恒（如能量守恒），导致在物理引擎中回放时出现漂移。本文提出KinemaForge，一种基于约束的端到端流水线，从短时RGB-D序列中联合推断部件几何、关节拓扑与参数，并通过基于可微分刚体动力学的能量一致性验证器进行校验。该方法包含三个组件：编码关节-部件关联的软边动力学约束图；通过Featherstone人工体算法反向传播从渲染观测到关节参数的可微分螺旋轴求解器；以及惩罚非物理解释自由响应的能量残差损失。在五个PartNet-Mobility类别及内部RGB-D基准上，相较于最强几何基线PARIS，平均关节轴误差由4.52°降至2.83°（降低37.4%）；相较交互式基线Ditto，由5.30°降至2.83°（降低46.6%）；50秒滚动回放中仿真漂移降低64%；初步评估显示其生成的URDF在闭环操控任务中的成功率提升14.6个百分点。代码与重建数据将在论文录用后发布。
原文摘要 · Abstract (English)
Reconstructing simulation-ready digital twins of articulated objects from sensor observations remains constrained by two persistent gaps: (i) part-level geometric reconstruction is decoupled from kinematic-parameter estimation, and (ii) the recovered models often violate basic dynamic invariants such as energy conservation, leading to drift when the URDF is replayed in physics simulators. We present KinemaForge, a constraint-driven pipeline that jointly infers part-level shape, joint topology, and joint parameters from short RGB-D sequences and validates the result against an energy-consistent verifier built on differentiable rigid-body dynamics. The pipeline introduces three components: a kinematic constraint graph that encodes joint-part incidences as soft edges; a differentiable screw-axis solver that backpropagates from rendered observations through Featherstone's articulated-body algorithm to joint parameters; and an energy residual loss that penalises non-physical free responses of the reconstructed model. Across five PartNet-Mobility categories and an internal RGB-D benchmark, KinemaForge reduces the average joint-axis error from 4.52 degrees to 2.83 degrees (-37.4%) over the strongest geometric baseline (PARIS) and from 5.30 degrees to 2.83 degrees (-46.6%) over the interaction-based Ditto baseline, lowers long-horizon simulation drift by 64% (vs. PARIS) over 50 s rollouts, and yields URDFs whose closed-loop manipulation success rate improves by 14.6 percentage points over Ditto in our preliminary evaluation. Code and reconstruction data will be released upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。