• DOI:10.1007/978-3-030-58536-5_43
Corpus ID: 220514513

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

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed