.png){kind=icon}
Return
Deep Geometric Texture Synthesis
.png){kind=icon}
OA
AI
DOI：10.1145/3386569.3392471.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 (Le., 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 (Le., 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.
Keywords:
Geometric Deep Learning
Surface Reconstruction
Shape Analysis
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.5
Papers:
4.8K
Citations:
3.6W
Organization
Cited Papers
In vivo DTI of the healthy and injured cat spinal cord at high spatial and angular resolution.png)
NeuroImage
NeuroImageIF0
PREAI
ShareSaveShareSave
Treatment, prognostic markers and survival in thymic neuroendocrine tumours. A study from a single tertiary referral centreLung Cancer
Lung CancerIF0
PREAI
ShareSaveShareSave
View more