论文标题
通过分析和与生成对抗网络合成的纹理表示
Texture Representation via Analysis and Synthesis with Generative Adversarial Networks
论文作者
论文摘要
我们通过分析和与生成对抗网络合成研究数据驱动的纹理建模。对于网络培训和测试，我们编制了一套在空间均匀的纹理中，从随机到常规。我们采用stylegan3进行合成，并证明它产生的纹理超出了培训数据中所示的质感。为了进行纹理分析，我们建议使用新型潜在领域重建一致性标准用于合成纹理，并进行迭代精致，并具有Gramian损失的真实纹理。我们提出了评估网络能力，探索潜在空间轨迹的全球和局部行为的知觉程序，并与现有的纹理分析合成技术进行比较。
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.
