Texture Representation via Analysis and Synthesis with Generative Adversarial Networks

2022/12/20 by Lin, Jue, Sharma, Gaurav, Pappas, Thrasyvoulos N. · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2212.09983

Abstract

We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to regular. We adopt StyleGAN3 for synthesis and demonstrate that it produces diverse textures beyond those represented in the training data. For texture analysis, we propose GAN inversion using a novel latent domain reconstruction consistency criterion for synthesized textures, and iterative refinement with Gramian loss for real textures. We propose perceptual procedures for evaluating network capabilities, exploring the global and local behavior of latent space trajectories, and comparing with existing texture analysis-synthesis techniques.

Cited by

• Extracting Voice Styles from Frozen TTS Models via Gradient-Based Inverse Optimization

Related

• User-Controllable Multi-Texture Synthesis with Generative Adversarial\n Networks
• Texture Synthesis with Spatial Generative Adversarial Networks
• Learning Texture Manifolds with the Periodic Spatial GAN
• GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
• Diversified Texture Synthesis with Feed-forward Networks