Generative Image Modeling using Style and Structure Adversarial Networks

@inproceedings{Wang2016GenerativeIM,
  title={Generative Image Modeling using Style and Structure Adversarial Networks},
  author={Xiaolong Wang and Abhinav Gupta},
  booktitle={ECCV},
  year={2016}
}
Current generative frameworks use end-to-end learning and generate images by sampling from uniform noise distribution. However, these approaches ignore the most basic principle of image formation: images are product of: (a) Structure: the underlying 3D model; (b) Style: the texture mapped onto structure. In this paper, we factorize the image generation process and propose Style and Structure Generative Adversarial Network (S-GAN). Our S-GAN has two components: the StructureGAN generates a… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 207 citations. REVIEW CITATIONS