Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 500

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting

Open access
Zeng, Yanhong, Fu, Jianlong, Chao, Hongyang, Guo, Baining·2019·2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2019.00158
Open this paper in CoChat — free account

Abstract

High-quality image inpainting requires filling missing regions in a damaged image with plausible content. Existing works either fill the regions by copying high-resolution patches or generating semantically-coherent patches from region context, while neglecting the fact that both visual and semantic plausibility are highly-demanded. In this paper, we propose a Pyramid-context Encoder Network (denoted as PEN-Net) for image inpainting by deep generative models. The proposed PEN-Net is built upon a U-Net structure with three tailored components, ie., a pyramid-context encoder, a multi-scale decoder, and an adversarial training loss. First, we adopt a U-Net as backbone which can encode the context of an image from high-resolution pixels into high-level semantic features, and decode the features reversely. Second, we propose a pyramid-context encoder, which progressively learns region affinity by attention from a high-level semantic feature map, and transfers the learned attention to its adjacent high-resolution feature map. As the missing content can be filled by attention transfer from deep to shallow in a pyramid fashion, both visual and semantic coherence for image inpainting can be ensured. Third, we further propose a multi-scale decoder with deeply-supervised pyramid losses and an adversarial loss. Such a design not only results in fast convergence in training, but more realistic results in testing. Extensive experiments on a broad range of datasets shows the superior performance of the proposed network.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr.2019.00158

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 19

  1. 10.1109/TPAMI.2017.2723009 · DOI · Paper page
  2. 10.1109/CVPR.2018.00577 · DOI · Paper page
  3. karras, 2018, Progressive growing of gans for improved quality, stability, and variation, ICLRE
  4. 10.1007/978-3-540-24673-2_31 · DOI · Paper page
  5. 10.1109/ICCV.2015.425 · DOI · Paper page
  6. miyato, 2018, Spectral normalization for generative adversarial networks, ICLRE
  7. ren, 2015, Shepard convolutional neural networks, NeurIPS, 901
  8. yan, 2018, Shift-net: Image inpainting via deep feature rearrangement, ECCV, 1
  9. 10.1109/TPAMI.2007.60 · DOI · Paper page
  10. 10.1109/CVPR.2003.1211536 · DOI
  11. 10.1145/383259.383296 · DOI · Paper page
  12. yang, 2017, High-resolution image inpainting using multiscale neural patch synthesis, CVPR, 6721
  13. efros, 1999, Texture synthesis by non-parametric sampling, ICCV, 1033
  14. 10.1145/344779.344972 · DOI · Paper page
  15. iizuka, 2017, Globally and locally consistent image completion, TOG, 36, 107, 10.1145/3072959.3073659 · DOI · Paper page
  16. barnes, 2009, Patchmatch: A randomized correspondence algorithm for structural image editing, TOG, 28, 24:1, 10.1145/1531326.1531330 · DOI · Paper page
  17. 10.1145/1073204.1073274 · DOI · Paper page
  18. 10.1007/978-3-030-01216-8_1 · DOI
  19. tylecek, 2013, Spatial pattern templates´ for recognition of objects with regular structure, GCPR, 364

Cited by

See all 500

Metadata

Authors
Zeng, Y., Fu, J., Chao, H., & Guo, B.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
1486-1494
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2019.00158
OpenAlex
W2936180003
Cited by
500
References
13
FWCI
20.49
Type
conference paper
Language
en
Open access
green
Licence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.