Learning to Synthesize Fashion Textures

TL;DR

This paper introduces a novel generative model specifically designed for fashion textures, utilizing Gram matrices, recursive auto-encoders, and Gaussian mixture models to produce realistic and diverse textures.

Contribution

The work presents a new approach tailored for fashion textures, incorporating scale dependency and multi-modality, which improves realism and diversity over existing models.

Findings

Outperforms state-of-the-art methods in realism and diversity.

Effectively models scale-dependent textures with recursive auto-encoders.

Enhances texture diversity using Gaussian mixture models.

Abstract

Existing unconditional generative models mainly focus on modeling general objects, such as faces and indoor scenes. Fashion textures, another important type of visual elements around us, have not been extensively studied. In this work, we propose an effective generative model for fashion textures and also comprehensively investigate the key components involved: internal representation, latent space sampling and the generator architecture. We use Gram matrix as a suitable internal representation for modeling realistic fashion textures, and further design two dedicated modules for modulating Gram matrix into a low-dimension vector. Since fashion textures are scale-dependent, we propose a recursive auto-encoder to capture the dependency between multiple granularity levels of texture feature. Another important observation is that fashion textures are multi-modal. We fit and sample from a Gaussian mixture model in the latent space to improve the diversity of the generated textures. Extensive experiments demonstrate that our approach is capable of synthesizing more realistic and diverse fashion textures over other state-of-the-art methods.