Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,928

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Free-Form Image Inpainting With Gated Convolution

Open access
Yu, Jiahui, Lin, Zhe, Yang, Jimei, Shen, Xiaohui, Lu, Xin, Huang, Thomas·2019·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2019.00457
Open this paper in CoChat — free account

Abstract

We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single rectangular mask are not applicable. Thus, we also present a patch-based GAN loss, named SN-PatchGAN, by applying spectral-normalized discriminator on dense image patches. SN-PatchGAN is simple in formulation, fast and stable in training. Results on automatic image inpainting and user-guided extension demonstrate that our system generates higher-quality and more flexible results than previous methods. Our system helps user quickly remove distracting objects, modify image layouts, clear watermarks and edit faces. Code, demo and models are available at: \url{https://github.com/JiahuiYu/generative_inpainting}.

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/iccv.2019.00457

Cites

9 of 9 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

Show all 9 references

Research works printed but not linked: 45

  1. srivastava, 2015, Highway networks, arXiv preprint arXiv 1505 00387
  2. song, 2018, Spg-net: Segmentation prediction and guidance network for image inpainting, arXiv preprint arXiv 1805 03356
  3. 10.1109/CVPR.2019.01162 · DOI
  4. pavic’, 2006, Interactive image completion with perspective correction, The Visual Computer, 22, 671, 10.1007/s00371-006-0050-2 · DOI
  5. 10.1007/978-3-030-01216-8_1 · DOI
  6. 10.1109/CVPR.2008.4587842 · DOI · Paper page
  7. shin, 2019, Pepsi++: Fast and lightweight network for image inpainting, arXiv preprint arXiv 1905 09010
  8. 10.1109/CVPR.2017.723 · DOI · Paper page
  9. van den oord, 2016, Conditional image generation with pixelcnn decoders, In Proceedings of the 30th International Conference on Neural Information Processing Systems, 4797
  10. 10.1109/83.935036 · DOI · Paper page
  11. 10.1145/364338.364405 · DOI · Paper page
  12. 10.1145/1073204.1073263 · DOI · Paper page
  13. 10.1109/CVPR.2017.624 · DOI · Paper page
  14. li, 2016, Precomputed real-time texture synthesis with markovian generative adversarial networks, in European Conference on Computer Vision, 702
  15. miyato, 2018, Spectral normalization for generative adversarial networks, arXiv preprint arxiv 1802 05807
  16. nazeri, 2019, Edgeconnect: Generative image inpainting with adversarial edge learning, arXiv preprint arXiv 1901 04217
  17. mount, 1998, ANN Library for Approximate Nearest Neighbour Searching
  18. zhang, 2017, Real-time user-guided image colorization with learned deep priors, ACM Transactions on Graphics (TOG), 36, 119, 10.1145/3072959.3073703 · DOI · Paper page
  19. 10.1109/WACV.2019.00166 · DOI
  20. zhou, 2017, Places: A 10 million image database for scene recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 3
  21. zheng, 2019, Pluralistic image completion, Proc IEEE Conf Computer Vision and Pattern Recognition, 1438
  22. 10.1145/1275808.1276382 · DOI · Paper page
  23. 10.1109/TPAMI.2014.2330611 · DOI
  24. 10.1145/1073204.1073274 · DOI · Paper page
  25. huang, 2014, Image completion using planar structure guidance, ACM Transactions on Graphics (TOG), 33, 129, 10.1145/2601097.2601205 · DOI · Paper page
  26. 10.1109/ICCPhot.2013.6528313 · DOI
  27. iizuka, 2017, Globally and locally consistent image completion, ACM Transactions on Graphics (TOG), 36, 107, 10.1145/3072959.3073659 · DOI · Paper page
  28. johnson, 2016, Perceptual losses for real-time style transfer and super-resolution, in European Conference on Computer Vision, 694
  29. karras, 2017, Progressive growing of gans for improved quality, stability, and variation, arXiv preprint arXiv 1710 10196
  30. 10.1109/CVPR.2019.00594 · DOI
  31. barnes, 2009, Patchmatch: A randomized correspondence algorithm for structural image editing, ACM Transactions on Graphics (TOG) (Proceedings of SIGGRAPH 2004), 10.1145/1531326.1531330 · DOI · Paper page
  32. dauphin, 2017, Language modeling with gated convolutional networks, In Proceedings of the 34th International Conference on Machine Learning-, 70, 933
  33. 10.1145/2185520.2185578 · DOI · Paper page
  34. 10.1145/383259.383296 · DOI · Paper page
  35. 10.1145/1201775.882267 · DOI · Paper page
  36. 10.1109/CVPR.2018.00577 · DOI · Paper page
  37. efros, 1999, Texture synthesis by non-parametric sampling. In Computer Vision, 1999, The Proceedings of the Seventh IEEE International Conference on, 2, 1033
  38. yang, 2018, Image inpainting using block-wise procedural training with annealed adversarial counterpart, arXiv preprint arXiv 1803 08943
  39. xiong, 2019, Foreground-aware image inpainting, Proc IEEE Conf Computer Vision and Pattern Recognition, 5840
  40. yu, 2018, Wide activation for efficient and accurate image super-resolution, arXiv preprint arXiv 1808 02194
  41. 10.1109/CVPR.2017.728 · DOI · Paper page
  42. 10.1109/CVPR.2018.00917 · DOI · Paper page
  43. 10.3390/rs9050446 · DOI · Paper page
  44. 10.1109/ICCV.2015.164 · DOI · Paper page
  45. 10.5244/C.23.116 · DOI

Cited by

Metadata

Authors
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., & Huang, T.
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
4470-4479
DOI
10.1109/iccv.2019.00457
OpenAlex
W2807633959
Cited by
1,928
References
9
FWCI
79.11
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.