Deep Geometric Texture Synthesis

Abstract

Recently, deep generative adversarial networks for image generation have advanced rapidly; yet, only a small amount of research has focused on generative models for irregular structures, particularly meshes. Nonetheless, mesh generation and synthesis remains a fundamental topic in computer graphics. In this work, we propose a novel framework for synthesizing geometric textures. It learns geometric texture statistics from local neighborhoods (i.e., local triangular patches) of a single reference 3D model. It learns deep features on the faces of the input triangulation, which is used to subdivide and generate offsets across multiple scales, without parameterization of the reference or target mesh. Our network displaces mesh vertices in any direction (i.e., in the normal and tangential direction), enabling synthesis of geometric textures, which cannot be expressed by a simple 2D displacement map. Learning and synthesizing on local geometric patches enables a genus-oblivious framework, facilitating texture transfer between shapes of different genus.

SIGGRAPH 2020

References in corpus (4)

• MeshCNN: A Network with an Edge
• Non-Stationary Texture Synthesis by Adversarial Expansion
• Multi-chart Generative Surface Modeling
• Cubic Stylization

Cited by in corpus (10)

• Subdivision-Based Mesh Convolution Networks
• SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps
• Learning to Generate 3D Shapes from a Single Example
• EASI-Tex: Edge-Aware Mesh Texturing from Single Image
• TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization
• Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art
• Surface Geometry Processing: An Efficient Normal-based Detail Representation
• Self-Parameterization Based Multi-Resolution Mesh Convolution Networks
• CageNet: A Meta-Framework for Learning on Wild Meshes
• Directional Texture Editing for 3D Models