用可控速度场生成可动机械结构，支持动作与形态双重控制。
ArticFlow: Generative Simulation of Articulated Mechanisms
- 两阶段流匹配框架，结合隐空间与点云流实现动作控制
- 在MuJoCo数据集上生成精度高于专用模拟器和静态生成模型
- 可同时用于生成新形态与预测动作下的运动轨迹
生成模型在静态3D形状生成上已取得显著进展，但可动3D结构因动作依赖形变和数据集有限仍具挑战。我们提出ArticFlow，一种两阶段流匹配框架，通过显式动作控制学习从噪声到目标点云的可控速度场。该方法结合（i）将噪声映射到形状先验编码的隐空间流，以及（ii）基于动作与形状先验条件化的点云流，使单一模型能表征多样可动类别并跨动作泛化。在MuJoCo Menagerie数据集上，ArticFlow兼具生成模型与神经模拟器功能：从紧凑先验预测动作相关运动学，并通过隐空间插值合成新形态。相比对象特定模拟器及静态点云生成的动作用变体，ArticFlow在运动学精度与形状质量上均表现更优。结果表明，动作条件流匹配是实现可控、高质量可动机构生成的可行路径。
原文摘要 · Abstract (English)
Recent advances in generative models have produced strong results for static 3D shapes, whereas articulated 3D generation remains challenging due to action-dependent deformations and limited datasets. We introduce ArticFlow, a two-stage flow matching framework that learns a controllable velocity field from noise to target point sets under explicit action control. ArticFlow couples (i) a latent flow that transports noise to a shape-prior code and (ii) a point flow that transports points conditioned on the action and the shape prior, enabling a single model to represent diverse articulated categories and generalize across actions. On MuJoCo Menagerie, ArticFlow functions both as a generative model and as a neural simulator: it predicts action-conditioned kinematics from a compact prior and synthesizes novel morphologies via latent interpolation. Compared with object-specific simulators and an action-conditioned variant of static point-cloud generators, ArticFlow achieves higher kinematic accuracy and better shape quality. Results show that action-conditioned flow matching is a practical route to controllable and high-quality articulated mechanism generation.
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。