Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives

Xiaoxu Meng, Zhongmin Chen, Bo Yang, Weikai Chen, Weixiao Liu, Lin Gao

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.

DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives

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.
Paper Structure (33 sections, 19 equations, 7 figures, 2 tables)

This paper contains 33 sections, 19 equations, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Neural Implicit Reconstructions.
  4. Reconstruction from Model Retrieval and Constructive Methods.
  5. Superquadric Reconstruction via Differentiable Rendering.
  6. Artist-Created Mesh Generation.
  7. Method
  8. Formulation
  9. Renderer
  10. Implicit Surface Estimation.
  11. Probability Density Estimation.
  12. Mesh Exportation
  13. Optimization
  14. Training Objectives
  15. Redundant Suppression.
  16. ...and 18 more sections

Figures (7)

  • Figure 1: DualPrim is a differentiable representation that models 3D shapes using dual-primitives composed of positive- and negative-density superquadrics. This additive-subtractive design increases the representational power (e.g. holes and concavities) without sacrificing compactness or differentiability. Integrated into a volumetric differentiable renderer, DualPrim supports end-to-end learning from multi-view images and enables seamless mesh extraction through closed-form Boolean differencing. Our method produces compact, structured, and interpretable reconstructions that better meet downstream requirements than additive-only approaches.
  • Figure 2: The first row shows the artist-created meshes (AMs), and the second row shows the exportation from Marching Cubes marching_cubes.
  • Figure 3: The overview of DualPrim pipeline. We represent the 3D scene as a set of primitive parameters and optimize them within a differentiable rendering framework under multi-view image supervision. The final mesh is obtained by computing the Boolean difference between the positive and negative superquadric components of each primitive.
  • Figure 4: Illustration of the SDF calculation with PSQ and NSQ.
  • Figure 5: We show the rendering of three example dual-primitives.
  • ...and 2 more figures