用可微分基元实现结构化动态物体的高保真建模
D-Prism: Differentiable Primitives for Structured Dynamic Modeling
- 将3DGS与基元表面结合，兼顾外观与几何精度
- 引入变形网络控制基元运动，实现精准轨迹跟踪
- 自适应调整基元数量，更好匹配真实空间范围
对多部件装配体或铰接机构等结构化动态物体，同时捕捉其几何形状与刚性运动仍是关键挑战。现有动态方法如可变形网格或3DGS依赖非结构化表示，难以联合建模合适的几何与关节运动。基于基元的方法在静态结构场景中表现优异，但其动态潜力尚未探索。本文提出D-Prism，首个将可微分基元拓展至动态领域的高保真结构化动态建模框架。具体而言，将3DGS绑定至基元表面，融合二者在外观与几何上的优势；引入变形网络控制基元运动，确保准确匹配物体实际运动；设计新型自适应控制策略，动态调整基元数量，更贴合物体的真实空间占据范围。实验表明，该方法在结构化动态建模上表现卓越，兼具结构化几何与精确运动追踪能力。
原文摘要 · Abstract (English)
Capturing both geometry and rigid motion for structured dynamic objects, like multi-part assemblies or jointed mechanisms, remains a key challenge. Existing dynamic methods, such as deformable meshes or 3DGS, rely on unstructured representations and fail to jointly model suitable geometry and articulated motion. Primitive-based methods excel at structured static scenes, but their dynamic potential is still unexplored. We propose D-Prism, the first framework to achieve high-fidelity structured dynamic modeling by extending differentiable primitives to the dynamic domain. Specifically, we bind 3DGS to primitive surfaces, leveraging their respective strengths in appearance and geometry. We introduce a deformation network to control primitive motion, ensuring it accurately matches the object's movement. Furthermore, we design a novel adaptive control strategy to dynamically adjust primitive counts, better matching objects' true spatial footprint. Experiments confirm that our method excels at structured dynamic modeling, providing both structured geometry and precise motion tracking.
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。