Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,916

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Deep Image Prior

Lempitsky, Victor, Vedaldi, Andrea, Ulyanov, Dmitry·2018·2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
DOI 10.1109/cvpr.2018.00984
Open this paper in CoChat — free account

Abstract

Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, superresolution, and inpainting. Furthermore, the same prior can be used to invert deep neural representations to diagnose them, and to restore images based on flash-no flash input pairs. Apart from its diverse applications, our approach highlights the inductive bias captured by standard generator network architectures. It also bridges the gap between two very popular families of image restoration methods: learning-based methods using deep convolutional networks and learning-free methods based on handcrafted image priors such as self-similarity.

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.2018.00984

Cites

6 of 6 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 6 references

Research works printed but not linked: 27

  1. zhang, 2017, Understanding deep learning requires rethinking generalization, Proc ICLR
  2. zeyde, 2010, On single image scale-up using sparse-representations, Curves and Surfaces, 711
  3. 10.1109/CVPR.2010.5539957 · DOI · Paper page
  4. ulyanov, 0, Deep Image Prior webpage
  5. goodfellow, 2014, Generative adversarial nets, Proc NIPS, 2672
  6. 10.1109/ICCV.2015.212 · DOI · Paper page
  7. 10.1109/CVPR.2015.7299149 · DOI
  8. iizuka, 2017, Globally and Locally Consistent Image Completion, ACM Trans Graphics (Proc ACM SIGGRAPH), 36, 107:1
  9. 10.1109/CVPR.2017.618 · DOI · Paper page
  10. 10.1109/ICCV.2017.481 · DOI · Paper page
  11. 10.1109/CVPR.2005.38 · DOI · Paper page
  12. ren, 2015, Shepard convolutional neural networks, Proc NIPS, 901
  13. bojanowski, 2017, Optimizing the latent space of generative networks
  14. 10.1109/TIP.2007.901238 · DOI · Paper page
  15. 10.1109/CVPR.2017.298 · DOI · Paper page
  16. 10.1109/CVPR.2012.6247952 · DOI · Paper page
  17. dosovitskiy, 2016, Inverting convolutional networks with convolutional networks, Proc CVPR
  18. dong, 2014, Learning a deep convolutional network for image super-resolution, Proc ECCV, 184
  19. 10.5244/C.26.135 · DOI · Paper page
  20. 10.1109/CVPR.2015.7298761 · DOI · Paper page
  21. 10.1109/ICCV.2017.356 · DOI
  22. lefkimmiatis, 2016, Non-local color image denoising with convolutional neural networks, Proc CVPR
  23. mahendran, 2016, Visualizing deep convolutional neural networks using natural pre-images, IJCV, 10.1007/s11263-016-0911-8 · DOI · Paper page
  24. papyan, 2017, Convolutional neural networks analyzed via convolutional sparse coding, Journal of Machine Learning Research, 18, 1
  25. mairal, 2010, Online learning for matrix factorization and sparse coding, Journal of Machine Learning Research, 11, 19
  26. 10.1145/1015706.1015777 · DOI · Paper page
  27. 10.1109/ICCV.2017.566 · DOI

Cited by

Metadata

Authors
Lempitsky, V., Vedaldi, A., & Ulyanov, D.
Venue
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Published
2018-06
Pages
9446-9454
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2018.00984
OpenAlex
W2964013315
Cited by
1,916
References
6
FWCI
63.69
Type
conference paper
Language
en
Open access
closed

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.