Corpus ID: 208291394

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation

@article{Li2019MixNMatchMD,
  title={MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation},
  author={Yuheng Li and Krishna Vijay Kumar Singh and Utkarsh Ojha and Yong Jae Lee},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.11758}
}
  • Yuheng Li, Krishna Vijay Kumar Singh, +1 author Yong Jae Lee
  • Published 2019
  • Computer Science, Engineering
  • ArXiv
  • We present MixNMatch, a conditional generative model that learns to disentangle and encode background, object pose, shape, and texture from real images with minimal supervision, for mix-and-match image generation. We build upon FineGAN, an unconditional generative model, to learn the desired disentanglement and image generator, and leverage adversarial joint image-code distribution matching to learn the latent factor encoders. MixNMatch requires bounding boxes during training to model… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    The Creation and Detection of Deepfakes: A Survey

    VIEW 1 EXCERPT

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 54 REFERENCES

    Disentangled Person Image Generation

    VIEW 3 EXCERPTS

    A Style-Based Generator Architecture for Generative Adversarial Networks

    VIEW 1 EXCERPT

    Style and Content Disentanglement in Generative Adversarial Networks

    VIEW 3 EXCERPTS

    Large Scale Adversarial Representation Learning

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Image-to-Image Translation with Conditional Adversarial Networks

    VIEW 1 EXCERPT

    StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

    VIEW 1 EXCERPT