SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields

TL;DR

SQuadGen is a diffusion-based framework that uses Chart Distance Fields to generate simple, artist-friendly quad mesh layouts on 3D shapes, overcoming data scarcity and connectivity challenges.

Contribution

It introduces CDF as a continuous surface representation and constructs a large dataset of quad layouts, enabling effective learning and synthesis of simple quad meshes.

Findings

SQuadGen outperforms existing methods in producing simple quad layouts.

The approach effectively addresses mesh connectivity and data scarcity issues.

Generated layouts are robust and suitable for artistic editing.

Abstract

3D shapes from scanning, reconstruction, or AI-generated content often lack simple quad mesh layouts -- critical for efficient editing and modeling. Existing quad-remeshing techniques typically produce complex layouts with irregular loops, leading to tedious manual cleanup and extensive algorithm tuning. We introduce SQuadGen, a diffusion-based generative framework that leverages Chart Distance Fields (CDF) to synthesize simple quad layouts on 3D shapes. Our approach addresses two key challenges: (1) the discrete nature of mesh connectivity, which hinders learning, and (2) the scarcity of large-scale datasets with simple quad meshes. To overcome the first, we propose CDF, a continuous surface-based representation enabling effective learning and synthesis of quad layouts. To address the second, we define loop-aware simplicity metrics and construct a large-scale dataset of high-quality quad layouts recovered from public 3D repositories through a robust quad-recovery pipeline. Extensive evaluations across diverse 3D inputs show that SQuadGen consistently outperforms existing methods, producing robust, artist-friendly simple quad layouts.