D-Prism: Differentiable Primitives for Structured Dynamic Modeling

TL;DR

D-Prism is a novel framework that extends differentiable primitives to dynamic modeling, enabling high-fidelity structured geometry and motion tracking for articulated objects.

Contribution

It introduces a deformation network and adaptive primitive control to accurately model and track structured dynamic objects, a novel approach in this domain.

Findings

Outperforms existing methods in structured dynamic modeling tasks.

Provides high-fidelity geometry and motion tracking for articulated objects.

Successfully adapts primitive counts to match object complexity.

Abstract

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.