Corpus ID: 220713507

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

@article{Jiang2020TSITAS,
  title={TSIT: A Simple and Versatile Framework for Image-to-Image Translation},
  author={Liming Jiang and Changxu Zhang and Mingyang Huang and Chunxiao Liu and Jianping Shi and Chen Change Loy},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.12072}
}
  • Liming Jiang, Changxu Zhang, +3 authors Chen Change Loy
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • We introduce a simple and versatile framework for image-toimage translation. We unearth the importance of normalization layers, and provide a carefully designed two-stream generative model with newly proposed feature transformations in a coarse-to-fine fashion. This allows multi-scale semantic structure information and style representation to be effectively captured and fused by the network, permitting our method to scale to various tasks in both unsupervised and supervised settings. No… CONTINUE READING

    References

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

    Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization

    VIEW 21 EXCERPTS
    HIGHLY INFLUENTIAL

    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Multimodal Unsupervised Image-to-Image Translation

    VIEW 18 EXCERPTS
    HIGHLY INFLUENTIAL

    Semantic Image Synthesis With Spatially-Adaptive Normalization

    VIEW 20 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Conditional Generative Adversarial Nets

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL