DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives

2026-03-17

AI Summary

Existing neural 3D reconstruction methods often prioritize fidelity at the expense of structural plausibility, yielding overly dense meshes with chaotic topology and absent semantic part boundaries, which hinders editability and reuse. This work proposes a compact and structured reconstruction framework that introduces, for the first time, a joint additive-subtractive superquadric representation: positive primitives form the base shape, while negative primitives carve holes and concavities through differentiable Boolean difference operations, enabling topology-aware modeling. The method supports end-to-end learning from multi-view images, leverages a voxel-based differentiable renderer for efficient optimization, and directly outputs high-quality meshes with clear semantic structure. Experiments demonstrate that our approach significantly outperforms existing techniques—particularly those relying solely on additive primitives—in reconstruction accuracy, model compactness, and structural interpretability.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Structured Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• 3D reconstruction
• structured representation
• mesh topology
• part boundaries
• asset reuse

Innovation

• DualPrim
• positive and negative primitives
• superquadrics
• differentiable rendering
• structured 3D reconstruction