STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?

Abstract

Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography. 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 extend the given 2D exemplar to arbitrary 3D solid textures. In STS-GAN, multi-scale 2D texture discriminators evaluate the similarity between the given 2D exemplar and slices from the generated 3D texture, promoting the 3D texture generator synthesizing realistic solid textures. Finally, experiments demonstrate that the proposed method can generate high-fidelity solid textures with similar visual characteristics to the 2D exemplar.

Cite

Text

Zhao et al. "STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/196

Markdown

[Zhao et al. "STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/zhao2023ijcai-sts/) doi:10.24963/IJCAI.2023/196

BibTeX

@inproceedings{zhao2023ijcai-sts,
  title     = {{STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?}},
  author    = {Zhao, Xin and Guo, Jifeng and Wang, Lin and Li, Fanqi and Li, Jiahao and Zheng, Junteng and Yang, Bo},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {1768-1776},
  doi       = {10.24963/IJCAI.2023/196},
  url       = {https://mlanthology.org/ijcai/2023/zhao2023ijcai-sts/}
}