Deep Image Harmonization

@article{Tsai2017DeepIH,
  title={Deep Image Harmonization},
  author={Yi-Hsuan Tsai and Xiaohui Shen and Zhe L. Lin and Kalyan Sunkavalli and Xin Lu and Ming-Hsuan Yang},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={2799-2807}
}
  • Yi-Hsuan Tsai, Xiaohui Shen, +3 authors Ming-Hsuan Yang
  • Published 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Compositing is one of the most common operations in photo editing. [...] Key Method We also introduce an efficient way to collect large-scale and high-quality training data that can facilitate the training process. Experiments on the synthesized dataset and real composite images show that the proposed network outperforms previous state-of-the-art methods.Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 64 CITATIONS

    Temporally Coherent Video Harmonization Using Adversarial Networks

    VIEW 10 EXCERPTS
    CITES METHODS, BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    DoveNet: Deep Image Harmonization via Domain Verification

    VIEW 9 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Improving the Harmony of the Composite Image by Spatial-Separated Attention Module

    VIEW 20 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Guided Image Inpainting: Replacing an Image Region by Pulling Content From Another Image

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Photographic style transfer

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Where and Who? Automatic Semantic-Aware Person Composition

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 14 Highly Influenced Citations

    • Averaged 21 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    Context Encoders: Feature Learning by Inpainting

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning a Discriminative Model for the Perception of Realism in Composite Images

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Colorful Image Colorization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Error-Tolerant Image Compositing

    VIEW 1 EXCERPT