LOGAN: Unpaired Shape Transform in Latent Overcomplete Space

@article{Yin2019LOGANUS,
  title={LOGAN: Unpaired Shape Transform in Latent Overcomplete Space},
  author={Kangxue Yin and Zhiqin Chen and Hui Huang and Daniel Cohen-Or and Hongxing Zhang},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.10170}
}
  • Kangxue Yin, Zhiqin Chen, +2 authors Hongxing Zhang
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • We introduce LOGAN, a deep neural network aimed at learning general-purpose shape transforms from unpaired domains. The network is trained on two sets of shapes, e.g., tables and chairs, while there is neither a pairing between shapes from the domains as supervision nor any point-wise correspondence between any shapes. Once trained, LOGAN takes a shape from one domain and transforms it into the other. Our network consists of an autoencoder to encode shapes from the two input domains into a… CONTINUE READING

    References

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

    DualGAN: Unsupervised Dual Learning for Image-to-Image Translation

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

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

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised Cross-Domain Image Generation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    P2P-NET

    VIEW 5 EXCERPTS

    Automatic unpaired shape deformation transfer

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

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

    VIEW 2 EXCERPTS

    Improved Training of Wasserstein GANs

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL