SPARK：借助视觉语言模型知识的可仿真部件级铰接重建
SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge
把 VLM 先验（粗 URDF、部件参考图、开合状态监督）注入扩散 Transformer 做部件级形状合成，再用可微前向运动学在图像监督下优化连续运动参数，为单图生成可仿真铰接资产提供了可复用的「语言先验 + 可微物理」流程。
原文依据 integrate the part-image guidance and the inferred structure graph into a diffusion transformer
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论铰接三维物体对具身智能、机器人和场景理解至关重要，但制作可仿真的资产仍然劳动密集，并且需要专家对部件层级与运动结构进行建模。我们提出 SPARK，一个从单张 RGB 图像重建物理一致、具有运动学部件级结构的铰接物体的框架。给定图像后，我们首先利用视觉语言模型提取粗略的 URDF 参数并生成部件级参考图像。随后，我们将部件图像引导与推断出的结构图整合进扩散 Transformer，以合成铰接物体各部件的一致形状与整体形状。为进一步细化 URDF 参数，我们探索了基于视觉语言模型的重新预测策略以细化离散属性，并设计了可微前向运动学模块，在视觉语言模型生成的开合状态监督下优化连续参数。大量实验表明，SPARK 能在多种类别上生成高质量、可直接用于仿真的铰接资产，并支撑机器人操作与交互建模等下游应用。
英文原文摘要 1113 字符
Articulated 3D objects are critical for embodied AI, robotics, and scene understanding, yet creating simulation-ready assets remains labor-intensive and requires expert modeling of part hierarchies and motion structures. We introduce SPARK, a framework for reconstructing physically consistent, kinematic part-level articulated objects from a single RGB image. Given the image, we first leverage VLMs to extract coarse URDF parameters and generate part-level reference images. We then integrate the part-image guidance and the inferred structure graph into a diffusion transformer to synthesize consistent part and complete shapes of articulated objects. To further refine the URDF parameters, we explore a VLM-based reprediction strategy for discrete attribute refinement and a differentiable forward kinematics module for continuous parameter optimization under VLM-generated open-state supervision. Extensive experiments show that SPARK produces high-quality, simulation-ready articulated assets across diverse categories, enabling downstream applications such as robotic manipulation and interaction modeling.