DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives
This addresses the need for more editable and reusable 3D assets in computer graphics and vision, though it is an incremental improvement over existing primitive-based methods.
The paper tackled the problem of neural 3D reconstructions producing dense, unstructured meshes that hinder editing and reuse, by introducing DualPrim, a framework using positive and negative superquadrics for compact and structured reconstruction, which achieved state-of-the-art accuracy.
Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives.