Corpus ID: 208512930

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization

@article{Zhu2019SEANIS,
  title={SEAN: Image Synthesis with Semantic Region-Adaptive Normalization},
  author={Peihao Zhu and Rameen Abdal and Yipeng Qin and Peter Wonka},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.12861}
}
  • Peihao Zhu, Rameen Abdal, +1 author Peter Wonka
  • Published 2019
  • Computer Science, Engineering
  • ArXiv
  • We propose semantic region-adaptive normalization (SEAN), a simple but effective building block for Generative Adversarial Networks conditioned on segmentation masks that describe the semantic regions in the desired output image. Using SEAN normalization, we can build a network architecture that can control the style of each semantic region individually, e.g., we can specify one style reference image per region. SEAN is better suited to encode, transfer, and synthesize style than the best… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 60 REFERENCES

    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Semantic Image Synthesis With Spatially-Adaptive Normalization

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    A Style-Based Generator Architecture for Generative Adversarial Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Learning Face Attributes in the Wild

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    The Cityscapes Dataset for Semantic Urban Scene Understanding

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Neural Algorithm of Artistic Style

    VIEW 3 EXCERPTS