User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks

@article{Ci2018UserGuidedDA,
  title={User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks},
  author={Yuanzheng Ci and Xinzhu Ma and Zhihui Wang and Haojie Li and Zhongxuan Luo},
  journal={Proceedings of the 26th ACM international conference on Multimedia},
  year={2018}
}
  • Yuanzheng Ci, Xinzhu Ma, +2 authors Zhongxuan Luo
  • Published 2018
  • Computer Science
  • Proceedings of the 26th ACM international conference on Multimedia
  • Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack of authentic illustration-line art training pairs also increases difficulty of model generalization. [...] Key Method Specifically, we integrate the conditional framework with WGAN-GP criteria as well as the perceptual loss to enable us to robustly train a deep network that makes the synthesized images more natural and real.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 19 CITATIONS

    Line Art Correlation Matching Network for Automatic Animation Colorization

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND

    Semi-Auto Sketch Colorization Based on Conditional Generative Adversarial Networks

    • Zijuan Cheng, Fang Meng, Jingbo Mao
    • Computer Science
    • 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
    • 2019
    VIEW 2 EXCERPTS

    SmartPaint: a co-creative drawing system based on generative adversarial networks

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Adversarial Colorization of Icons Based on Contour and Color Conditions

    VIEW 9 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Adversarial Colorization Of Icons Based On Structure And Color Conditions

    VIEW 9 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    Automatic Temporally Coherent Video Colorization

    Deep Line Art Video Colorization with a Few References

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 13 REFERENCES

    High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    cGAN-Based Manga Colorization Using a Single Training Image

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Real-time user-guided image colorization with learned deep priors

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Image-to-Image Translation with Conditional Adversarial Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Improved Training of Wasserstein GANs

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Generative Adversarial Nets

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL