PCGAN: Partition-Controlled Human Image Generation


  • Dong Liang Chinese Academy of Sciences
  • Rui Wang University of Chinese Academy of Sciences
  • Xiaowei Tian Chinese Academy of Sciences
  • Cong Zou Chinese Academy of Sciences




Human image generation is a very challenging task since it is affected by many factors. Many human image generation methods focus on generating human images conditioned on a given pose, while the generated backgrounds are often blurred. In this paper, we propose a novel Partition-Controlled GAN to generate human images according to target pose and background. Firstly, human poses in the given images are extracted, and foreground/background are partitioned for further use. Secondly, we extract and fuse appearance features, pose features and background features to generate the desired images. Experiments on Market-1501 and DeepFashion datasets show that our model not only generates realistic human images but also produce the human pose and background as we want. Extensive experiments on COCO and LIP datasets indicate the potential of our method.




How to Cite

Liang, D., Wang, R., Tian, X., & Zou, C. (2019). PCGAN: Partition-Controlled Human Image Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8698-8705. https://doi.org/10.1609/aaai.v33i01.33018698



AAAI Technical Track: Vision