One-to-one Mapping for Unpaired Image-to-image Translation

@article{Shen2020OnetooneMF,
  title={One-to-one Mapping for Unpaired Image-to-image Translation},
  author={Zengming Shen and S. Zhou and Y. Chen and B. Georgescu and X. Liu and T. Huang},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={1159-1168}
}
  • Zengming Shen, S. Zhou, +3 authors T. Huang
  • Published 2020
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • Recently image-to-image translation has attracted significant interests in the literature, starting from the successful use of the generative adversarial network (GAN), to the introduction of cyclic constraint, to extensions to multiple domains. [...] Key Method Building on top of CycleGAN, we learn a self-inverse function by simply augmenting the training samples by swapping inputs and outputs during training and with separated cycle consistency loss for each mapping direction. The outcome of such learning is…Expand Abstract

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES

    Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Harmonic Unpaired Image-to-image Translation

    VIEW 2 EXCERPTS

    StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

    VIEW 2 EXCERPTS

    Image-to-Image Translation with Conditional Adversarial Networks

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Toward Multimodal Image-to-Image Translation

    VIEW 3 EXCERPTS

    Unsupervised Image-to-Image Translation Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Towards Instance-Level Image-To-Image Translation

    DRIT++: Diverse Image-to-Image Translation via Disentangled Representations

    VIEW 1 EXCERPT