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

@article{Cun2020ImprovingTH,
  title={Improving the Harmony of the Composite Image by Spatial-Separated Attention Module},
  author={Xiaodong Cun and Chi-Man Pun},
  journal={IEEE Transactions on Image Processing},
  year={2020},
  volume={29},
  pages={4759-4771}
}
  • Xiaodong Cun, Chi-Man Pun
  • Published 2020
  • Mathematics, Medicine, Computer Science
  • IEEE Transactions on Image Processing
  • Image composition is one of the most important applications in image processing. However, the inharmonious appearance between the spliced region and background degrade the quality of the image. Thus, we address the problem of Image Harmonization: Given a spliced image and the mask of the spliced region, we try to harmonize the “style” of the pasted region with the background (non-spliced region). Previous approaches have been focusing on learning directly by the neural network. In this work, we… CONTINUE READING
    Deep Image Harmonization via Domain Verification
    2
    DoveNet: Deep Image Harmonization via Domain Verification
    5
    Foreground-aware Semantic Representations for Image Harmonization
    Supplementary Material for DoveNet: Deep Image Harmonization via Domain Verification
    BargainNet: Background-Guided Domain Translation for Image Harmonization

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 50 REFERENCES
    Deep Image Harmonization
    72
    Multi-scale image harmonization
    82
    Generative Image Inpainting with Contextual Attention
    545
    Temporally Coherent Video Harmonization Using Adversarial Networks
    5
    Free-Form Image Inpainting With Gated Convolution
    229
    Rethinking Atrous Convolution for Semantic Image Segmentation
    1629
    Perceptual Losses for Real-Time Style Transfer and Super-Resolution
    3328
    Attention-GAN for Object Transfiguration in Wild Images
    62
    Multi-scale noise estimation for image splicing forgery detection
    29