Learning in a Single Domain for Non-Stationary Multi-Texture Synthesis

TL;DR

This paper introduces a novel single-model approach for non-stationary multi-texture synthesis that captures multiple textures at various scales, with a category-specific training strategy and an objective evaluation metric, demonstrating superior performance.

Contribution

The paper presents the first unified model, training scheme, and evaluation metric for non-stationary multi-texture synthesis, enabling multi-pattern generation without fine-tuning.

Findings

Achieves high-quality multi-texture synthesis with efficient computation.

Handles textures of different categories with a category-specific training strategy.

Demonstrates superior performance over existing methods.

Abstract

This paper aims for a new generation task: non-stationary multi-texture synthesis, which unifies synthesizing multiple non-stationary textures in a single model. Most non-stationary textures have large scale variance and can hardly be synthesized through one model. To combat this, we propose a multi-scale generator to capture structural patterns of various scales and effectively synthesize textures with a minor cost. However, it is still hard to handle textures of different categories with different texture patterns. Therefore, we present a category-specific training strategy to focus on learning texture pattern of a specific domain. Interestingly, once trained, our model is able to produce multi-pattern generations with dynamic variations without the need to finetune the model for different styles. Moreover, an objective evaluation metric is designed for evaluating the quality of texture expansion and global structure consistency. To our knowledge, ours is the first scheme for this challenging task, including model, training, and evaluation. Experimental results demonstrate the proposed method achieves superior performance and time efficiency. The code will be available after the publication.