GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing

TL;DR

This paper systematically analyze the learning mechanisms of recent intelligent smoothing methods and proposes a prior-free reinforcement learning model for intelligent mesh smoothing, which achieves state-of-the-art results among intelligent smoothing methods on 2D meshes and is 7.16 times faster than traditional optimization-based smoothing methods.

Abstract

Mesh smoothing methods can enhance mesh quality by eliminating distorted elements, leading to improved convergence in simulations. To balance the efficiency and robustness of traditional mesh smoothing process, previous approaches have employed supervised learning and reinforcement learning to train intelligent smoothing models. However, these methods heavily rely on labeled dataset or prior knowledge to guide the models' learning. Furthermore, their limited capacity to enhance mesh connectivity often restricts the effectiveness of smoothing. In this paper, we first systematically analyze the learning mechanisms of recent intelligent smoothing methods and propose a prior-free reinforcement learning model for intelligent mesh smoothing. Our proposed model integrates graph neural networks with reinforcement learning to implement an intelligent node smoothing agent and introduces, for the first time, a mesh connectivity improvement agent. We formalize mesh optimization as a Markov Decision Process and successfully train both agents using Twin Delayed Deep Deterministic Policy Gradient and Double Dueling Deep Q-Network in the absence of any prior data or knowledge. We verified the proposed model on both 2D and 3D meshes. Experimental results demonstrate that our model achieves feature-preserving smoothing on complex 3D surface meshes. It also achieves state-of-the-art results among intelligent smoothing methods on 2D meshes and is 7.16 times faster than traditional optimization-based smoothing methods. Moreover, the connectivity improvement agent can effectively enhance the quality distribution of the mesh.

Figures (3)

• Figure 1: 'Empty' figure only to serve as an example of long caption requiring more than one line. It is not typed centered but aligned on both sides.
• Figure 2: Here is a sample figure.
• Figure 3: For publications with color tables (i.e., publications not offering color throughout the paper) please observe: for the printed version -- and ONLY for the printed version -- color figures have to be placed in the last page. For the electronic version, which will be converted to PDF before making it available electronically, the color images should be embedded within the document. Optionally, other multimedia material may be attached to the electronic version.