Learning topological operations on meshes with application to block decomposition of polygons

TL;DR

This paper introduces a reinforcement learning framework that learns to improve mesh quality by applying local and global operations, aiming to reduce irregular nodes in polygon meshes.

Contribution

It presents a novel self-play reinforcement learning approach for mesh quality enhancement without relying on predefined heuristics.

Findings

Effective reduction of irregular nodes in meshes.

Outperforms traditional heuristic-based methods.

Applicable to unstructured triangular and quadrilateral meshes.

Abstract

We present a learning based framework for mesh quality improvement on unstructured triangular and quadrilateral meshes. Our model learns to improve mesh quality according to a prescribed objective function purely via self-play reinforcement learning with no prior heuristics. The actions performed on the mesh are standard local and global element operations. The goal is to minimize the deviation of the node degrees from their ideal values, which in the case of interior vertices leads to a minimization of irregular nodes.