Texture Representation via Analysis and Synthesis with Generative Adversarial Networks
This work addresses texture representation for computer vision applications, but it is incremental as it builds on existing GAN frameworks with specific adaptations.
The paper tackles texture modeling by combining analysis and synthesis using generative adversarial networks, specifically StyleGAN3, to generate diverse textures beyond training data and proposes GAN inversion methods with novel criteria for texture analysis, achieving results comparable to existing techniques.
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.