STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary Exemplars?

Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in numerous application domains. However, existing methods generally fail to accurately learn arbitrary textures, which may result in the failure to synthesize solid textures with high fidelity. In this paper, we propose a novel generative adversarial nets-based framework (STS-GAN) to hierarchically learn arbitrary solid textures. In STS-GAN, multi-scale discriminators evaluate the similarity between patch from exemplar and slice from the generated volume, promoting the generator synthesizing realistic solid textures. Finally, experimental results demonstrate that the proposed method can generate high-fidelity solid textures with similar visual characteristics to the exemplar.