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.
%0 Generic
%1 hertz2020geometric
%A Hertz, Amir
%A Hanocka, Rana
%A Giryes, Raja
%A Cohen-Or, Daniel
%D 2020
%K 2020 deep-learning geometry graphics texture
%T Deep Geometric Texture Synthesis
%U http://arxiv.org/abs/2007.00074
%X 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.
@misc{hertz2020geometric,
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.},
added-at = {2020-07-04T20:15:02.000+0200},
author = {Hertz, Amir and Hanocka, Rana and Giryes, Raja and Cohen-Or, Daniel},
biburl = {https://www.bibsonomy.org/bibtex/27834bbc1bfccb2eaf91cbdbbf6081522/analyst},
description = {[2007.00074] Deep Geometric Texture Synthesis},
interhash = {afb1ffb6a820d24e17bcba4c4c31fa6a},
intrahash = {7834bbc1bfccb2eaf91cbdbbf6081522},
keywords = {2020 deep-learning geometry graphics texture},
note = {cite arxiv:2007.00074Comment: SIGGRAPH 2020},
timestamp = {2020-07-04T20:15:02.000+0200},
title = {Deep Geometric Texture Synthesis},
url = {http://arxiv.org/abs/2007.00074},
year = 2020
}