Co-occurrence based texture synthesis

As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate. In this work, we turn to co-occurrence statistics, which have long been used for texture analysis, to learn a controllable texture synthesis mode...

Full description

Saved in:

Bibliographic Details
Published in:	Computational visual media (Beijing) 2022-06, Vol.8 (2), p.289-302
Main Authors:	Darzi, Anna, Lang, Itai, Taklikar, Ashutosh, Averbuch-Elor, Hadar, Avidan, Shai
Format:	Article
Language:	eng
Subjects:	Artificial Intelligence co-occurrence Computer Graphics Computer Science Crops Deep learning Generative adversarial networks generative adversarial networks (GANs) Image processing Image Processing and Computer Vision Methods Noise Representations Research Article Synthesis Texture texture synthesis User Interfaces and Human Computer Interaction
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate. In this work, we turn to co-occurrence statistics, which have long been used for texture analysis, to learn a controllable texture synthesis model. We propose a fully convolutional generative adversarial network, conditioned locally on co-occurrence statistics, to generate arbitrarily large images while having local, interpretable control over texture appearance. To encourage fidelity to the input condition, we introduce a novel differentiable co-occurrence loss that is integrated seamlessly into our framework in an end-to-end fashion. We demonstrate that our solution offers a stable, intuitive, and interpretable latent representation for texture synthesis, which can be used to generate smooth texture morphs between different textures. We further show an interactive texture tool that allows a user to adjust local characteristics of the synthesized texture by directly using the co-occurrence values.
ISSN:	2096-0433 2096-0662