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.

翻译：我们调查通过分析和合成与基因对抗网络进行数据驱动纹理模型的模型,为了进行网络培训和测试,我们汇编了一套从随机到常规的空间均匀质谱。我们采用了StyleGAN3来合成,并证明它产生的纹理比培训数据中描述的要多。关于纹理分析,我们建议GAN倒置使用一个新的潜在领域综合纹理重建一致性标准,并与Gramian损失相迭完善真实纹理。我们提出了评估网络能力、探索潜在空间轨迹的全球和地方行为以及与现有的纹理分析合成技术进行比较的认知程序。