Year: 2024
Type: conference-paper
Abstract: Recovering a high-level representation of geometric data is a fundamental goal in geometric modeling and computer graphics. In this paper, we introduce a data-driven approach to computing the spectrum of the Laplace-Beltrami operator of triangle meshes using graph convolutional networks. Specifically, we train graph convolutional networks on a large-scale dataset of synthetically generated triangle meshes, encoded with geometric data consisting of Voronoi areas, normalized edge lengths, and the Gauss map, to infer eigenvalues of 3D shapes. We attempt to address the ability of graph neural networks to capture global shape descriptors–including spectral information–that were previously inaccessible using existing methods from computer vision, and our paper exhibits promising signals suggesting that Laplace-Beltrami eigenvalues on discrete surfaces can be learned. Additionally, we perform ablation studies showing the addition of geometric data leads to improved accuracy.
Authors: Wu, Yingying, Fu, Roger, Peng, Richard, Chen, Qifeng
Language: English
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1453181110, Track 4: Advanced CI Coordination Ecosystem: Monitoring and Measurement Services, G2614460161, G3562386289, Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS), G4010157413, ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI), CAREER: Scalable Algorithmic Primitives for Data Science, Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT), G5367127336, G5464919783, G6671297155, Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI
OpenAlex ID: W7113009221
