Corpus ID: 211572773

Sketch-to-Art: Synthesizing Stylized Art Images From Sketches

@article{Liu2020SketchtoArtSS,
  title={Sketch-to-Art: Synthesizing Stylized Art Images From Sketches},
  author={Bingchen Liu and Kunpeng Song and Ahmed M. Elgammal},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.12888}
}
  • Bingchen Liu, Kunpeng Song, Ahmed M. Elgammal
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, the model can synthesize meaningful details with colors and textures. The model consists of three modules designed explicitly for better artistic style capturing and generation. Based on a GAN framework, a dual-masked mechanism is introduced to enforce the content constraints (from the sketch), and a feature-map… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES

    SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

    VIEW 19 EXCERPTS
    HIGHLY INFLUENTIAL

    Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN

    VIEW 2 EXCERPTS

    Scribbler: Controlling Deep Image Synthesis with Sketch and Color

    VIEW 2 EXCERPTS

    Semantic Image Synthesis With Spatially-Adaptive Normalization

    VIEW 1 EXCERPT

    Image Style Transfer Using Convolutional Neural Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Style Transfer: A Review

    VIEW 1 EXCERPT

    Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    A Style-Based Generator Architecture for Generative Adversarial Networks

    VIEW 1 EXCERPT