Skip to main content

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

Kosk, R., Southern, R., You, L., Bian, S., Kokke, W. and Maguire, G., 2024. Deep Spectral Meshes: Multi-Frequency Facial Mesh Processing with Graph Neural Networks. Electronics, 13 (4), 720.

Full text available as:

electronics-13-00720-v2.pdf - Published Version
Available under License Creative Commons Attribution.


DOI: 10.3390/electronics13040720


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’ geometric and perceptual quality. In this work, spectral meshes are introduced as a method to decompose mesh deformations into low-frequency and high-frequency deformations. These features of low- and high-frequency deformations are used for representation learning with graph convolutional networks. A parametric model for 3D facial mesh synthesis is built upon the proposed framework, exposing user parameters that control disentangled high- and low-frequency deformations. Independent control of deformations at different frequencies and generation of plausible synthetic examples are mutually exclusive objectives. A Conditioning Factor is introduced to leverage these objectives. Our model takes further advantage of spectral partitioning by representing different frequency levels with disparate, more suitable representations. Low frequencies are represented with standardised Euclidean coordinates, and high frequencies with a normalised deformation representation (DR). This paper investigates applications of our proposed approach in mesh reconstruction, mesh interpolation, and multi-frequency editing. It is demonstrated that our method improves the overall quality of generated meshes on most datasets when considering both the  (Formula presented.)  norm and perceptual Dihedral Angle Mesh Error (DAME) metrics.

Item Type:Article
Uncontrolled Keywords:shape modelling; spectral meshes; multi-frequency deformations; graph neural networks
Group:Faculty of Media & Communication
ID Code:39741
Deposited By: Symplectic RT2
Deposited On:25 Apr 2024 13:07
Last Modified:25 Apr 2024 13:07


Downloads per month over past year

More statistics for this item...
Repository Staff Only -