Corpus ID: 218870309

High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

@article{Zeng2020HighResolutionII,
  title={High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling},
  author={Yu Zeng and Zhe Lin and Jimei Yang and Jianming Zhang and Eli Shechtman and Huchuan Lu},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.11742}
}
  • Yu Zeng, Zhe Lin, +3 authors Huchuan Lu
  • Published 2020
  • Computer Science
  • ArXiv
  • Existing image inpainting methods often produce artifacts when dealing with large holes in real applications. To address this challenge, we propose an iterative inpainting method with a feedback mechanism. Specifically, we introduce a deep generative model which not only outputs an inpainting result but also a corresponding confidence map. Using this map as feedback, it progressively fills the hole by trusting only high-confidence pixels inside the hole at each iteration and focuses on the… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 37 REFERENCES

    Generative Image Inpainting with Contextual Attention

    VIEW 10 EXCERPTS

    Places: A 10 Million Image Database for Scene Recognition

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    Context Encoders: Feature Learning by Inpainting

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Free-Form Image Inpainting With Gated Convolution

    VIEW 8 EXCERPTS

    Generative Adversarial Nets

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Image Inpainting for Irregular Holes Using Partial Convolutions

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Can someone please remove the backpack and 'lead' from my sons back? would love to have this picture of my kids without it!