Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations

@inproceedings{Liu2020RethinkingII,
  title={Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations},
  author={Hongyu Liu and B. Jiang and Yibing Song and Wei Huang and C. Yang},
  booktitle={ECCV},
  year={2020}
}
  • Hongyu Liu, B. Jiang, +2 authors C. Yang
  • Published in ECCV 2020
  • Computer Science
  • Deep encoder-decoder based CNNs have advanced image inpainting methods for hole filling. While existing methods recover structures and textures step-by-step in the hole regions, they typically use two encoder-decoders for separate recovery. The CNN features of each encoder are learned to capture either missing structures or textures without considering them as a whole. The insufficient utilization of these encoder features limit the performance of recovering both structures and textures. In… CONTINUE READING
    4 Citations
    Generator Pyramid for High-Resolution Image Inpainting
    • PDF
    Image Inpainting with Contextual Reconstruction Loss
    • PDF
    Image Inpainting With Learnable Edge-Attention Maps
    • PDF
    Semantic Layout Manipulation with High-Resolution Sparse Attention
    • PDF

    References

    SHOWING 1-10 OF 46 REFERENCES
    Shift-Net: Image Inpainting via Deep Feature Rearrangement
    • 123
    • Highly Influential
    • PDF
    Generative Image Inpainting with Contextual Attention
    • 751
    • Highly Influential
    • PDF
    Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting
    • Y. Zeng, J. Fu, H. Chao, B. Guo
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 69
    • PDF
    Coherent Semantic Attention for Image Inpainting
    • 54
    • Highly Influential
    • PDF
    Context Encoders: Feature Learning by Inpainting
    • 2,278
    • Highly Influential
    • PDF
    StructureFlow: Image Inpainting via Structure-Aware Appearance Flow
    • 61
    • Highly Influential
    • PDF
    Free-Form Image Inpainting With Gated Convolution
    • 337
    • Highly Influential
    • PDF
    Semantic Image Inpainting with Deep Generative Models
    • 703
    • PDF
    Contextual-Based Image Inpainting: Infer, Match, and Translate
    • 77
    • PDF
    EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
    • 193
    • PDF