Deep Spectral Meshes: Multi-Frequency Facial Mesh Processing with Graph Neural Networks

arXiv:2402.10365v1 Announce Type: new
Abstract: With the rising popularity of virtual worlds, the importance of data-driven parametric models of 3D meshes has grown rapidly. Numerous applications, such as computer vision, procedural generation, and mesh editing, vastly rely on these models. However, current approaches do not allow for independent editing of deformations at different frequency levels. They also do not benefit from representing deformations at different frequencies with dedicated representations, which would better expose their properties and improve the generated meshes' …

abstract applications arxiv computer computer vision cs.cg cs.cv cs.gr current data data-driven editing graph graph neural networks importance independent mesh meshes networks neural networks parametric processing type virtual virtual worlds vision