TopGen: Learning Structural Layouts and Cross-Fields for Quadrilateral Mesh Generation

TL;DR

TopGen is a novel learning-based framework that predicts structural layouts and cross-fields from triangular meshes, enabling high-quality, editable quadrilateral mesh generation with improved robustness and efficiency.

Contribution

It introduces a dual-query decoder for simultaneous structural and cross-field prediction, mimicking manual modeling workflows and handling complex geometries effectively.

Findings

Outperforms existing methods in geometric fidelity.

Ensures topological edge flow rationality.

Robust to non-manifold and low-quality meshes.

Abstract

High-quality quadrilateral mesh generation is a fundamental challenge in computer graphics. Traditional optimization-based methods are often constrained by the topological quality of input meshes and suffer from severe efficiency bottlenecks, frequently becoming computationally prohibitive when handling high-resolution models. While emerging learning-based approaches offer greater flexibility, they primarily focus on cross-field prediction, often resulting in the loss of critical structural layouts and a lack of editability. In this paper, we propose TopGen, a robust and efficient learning-based framework that mimics professional manual modeling workflows by simultaneously predicting structural layouts and cross-fields. By processing input triangular meshes through point cloud sampling and a shape encoder, TopGen is inherently robust to non-manifold geometries and low-quality initial topologies. We introduce a dual-query decoder using edge-based and face-based sampling points as queries to perform structural line classification and cross-field regression in parallel. This integrated approach explicitly extracts the geometric skeleton while concurrently capturing orientation fields. Such synergy ensures the preservation of geometric integrity and provides an intuitive, editable foundation for subsequent quadrilateral remeshing. To support this framework, we also introduce a large-scale quadrilateral mesh dataset, TopGen-220K, featuring high-quality paired data comprising raw triangular meshes, structural layouts, cross-fields, and their corresponding quad meshes. Experimental results demonstrate that TopGen significantly outperforms existing state-of-the-art methods in both geometric fidelity and topological edge flow rationality.