ArtGen: 条件生成建模任意部分级状态的关节物体
ArtGen: Conditional Generative Modeling of Articulated Objects in Arbitrary Part-Level States
AI总结：
ArtGen通过条件扩散框架生成任意部分级状态的关节3D物体，采用跨状态采样和思维链推理模块，提升运动学一致性与结构先验推断。
摘要：
生成关节资产对于机器人、数字孪生和具身智能至关重要。现有的生成模型往往依赖于单视角输入表示闭合状态，导致由于几何形状与关节动力学之间的纠缠而产生模糊或不现实的运动学结构。为了解决这些挑战，我们引入了ArtGen，一种基于扩散的条件框架，能够从单视角图像或文本描述中生成具有准确几何结构和连贯运动学的关节3D物体，在任意部分级状态下。具体而言，ArtGen采用跨状态蒙特卡洛采样，以显式强制全局运动学一致性，减少结构-运动纠缠。此外，我们集成了一个思维链推理模块，以推断稳健的结构先验，例如部分语义、关节类型和连接性，指导一个稀疏专家扩散变压器，专门处理多样的运动学交互。此外，一个具有局部-全局注意机制的组合3D-VAE潜在先验有效捕捉了细粒度几何和全局部分级关系。在PartNet-Mobility基准上的广泛实验表明，ArtGen显著优于最先进的方法。
英文摘要：
Generating articulated assets is crucial for robotics, digital twins, and embodied intelligence. Existing generative models often rely on single-view inputs representing closed states, resulting in ambiguous or unrealistic kinematic structures due to the entanglement between geometric shape and joint dynamics. To address these challenges, we introduce ArtGen, a conditional diffusion-based framework capable of generating articulated 3D objects with accurate geometry and coherent kinematics from single-view images or text descriptions at arbitrary part-level states. Specifically, ArtGen employs cross-state Monte Carlo sampling to explicitly enforce global kinematic consistency, reducing structural-motion entanglement. Additionally, we integrate a Chain-of-Thought reasoning module to infer robust structural priors, such as part semantics, joint types, and connectivity, guiding a sparse-expert Diffusion Transformer to specialize in diverse kinematic interactions. Furthermore, a compositional 3D-VAE latent prior enhanced with local-global attention effectively captures fine-grained geometry and global part-level relationships. Extensive experiments on the PartNet-Mobility benchmark demonstrate that ArtGen significantly outperforms state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
