Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,154

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Deep Learning for Single Image Super-Resolution: A Brief Review

Open access
Yang, Wenming, Zhang, Xuechen, Tian, Yapeng, Wang, Wei, Xue, Jing-Hao, Liao, Qingmin·2019·IEEE Transactions on Multimedia
DOI 10.1109/tmm.2019.2919431
Open this paper in CoChat — free account

Abstract

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem that aims to obtain a high-resolution output from one of its low-resolution versions. Recently, powerful deep learning algorithms have been applied to SISR and have achieved state-of-the-art performance. In this survey, we review representative deep learning-based SISR methods and group them into two categories according to their contributions to two essential aspects of SISR: The exploration of efficient neural network architectures for SISR and the development of effective optimization objectives for deep SISR learning. For each category, a baseline is first established, and several critical limitations of the baseline are summarized. Then, representative works on overcoming these limitations are presented based on their original content, as well as our critical exposition and analyses, and relevant comparisons are conducted from a variety of perspectives. Finally, we conclude this review with some current challenges and future trends in SISR that leverage deep learning algorithms.

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/tmm.2019.2919431

Cites

30 of 30 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 30 references

Research works printed but not linked: 85

  1. 10.1016/j.tics.2007.09.004 · DOI · Paper page
  2. 10.1109/TIT.1956.1056810 · DOI · Paper page
  3. 10.1016/j.neunet.2014.09.003 · DOI · Paper page
  4. 10.1007/978-3-642-42054-2_58 · DOI
  5. 10.1109/TPAMI.2013.50 · DOI · Paper page
  6. 10.1109/72.279181 · DOI · Paper page
  7. 10.1016/0364-0213(90)90002-E · doi:10.1016/0364-0213(90)90002-e · Paper page
  8. 10.1109/TNNLS.2015.2468069 · DOI
  9. yu, 2014, A unified learning framework for single image super-resolution, IEEE Trans Neural Netw Learn Syst, 25, 780, 10.1109/TNNLS.2013.2281313 · DOI
  10. 10.1109/TMM.2016.2515997 · DOI
  11. 10.1007/978-3-642-27413-8_47 · DOI · Paper page
  12. timofte, 0, A+: Adjusted anchored neighborhood regression for fast super-resolution, Proc Asian Conf Comput Vis, 111
  13. 10.1109/ICCV.2013.241 · DOI · Paper page
  14. 10.1109/TMM.2016.2614427 · DOI
  15. 10.1109/TNNLS.2015.2512563 · DOI
  16. 10.1109/TNNLS.2015.2511069 · DOI
  17. 10.1109/CVPR.2018.00329 · DOI · Paper page
  18. 10.1109/CVPR.2015.7299003 · DOI · Paper page
  19. 10.1109/ICCV.2011.6126474 · DOI · Paper page
  20. abadi, 0, TensorFlow: A system for large-scale machine learning, Proc 11th USENIX Conf Operating Syst Des Implementation, 16, 265
  21. 10.1145/2647868.2654889 · DOI · Paper page
  22. 10.1007/978-3-319-46475-6_25 · DOI · Paper page
  23. 10.1007/978-3-319-10590-1_53 · DOI · Paper page
  24. 10.1109/CVPR.2016.206 · DOI · Paper page
  25. 10.1007/978-3-319-10593-2_25 · DOI · Paper page
  26. 10.1109/CVPR.2016.207 · DOI · Paper page
  27. 10.1109/MSP.2003.1203207 · DOI · Paper page
  28. goodfellow, 2016, Deep Learning, 1
  29. goodfellow, 0, Generative adversarial nets, Proc Advances Neural Inf Process Syst, 2672
  30. 10.1007/978-3-319-10593-2_13 · DOI · Paper page
  31. 10.1162/NECO_a_00311 · DOI · Paper page
  32. 10.1109/CVPR.2018.00652 · DOI · Paper page
  33. arjovsky, 0, Wasserstein generative adversarial networks, Proc Int Conf Mach Learn, 214
  34. szegedy, 0, Inception-v4, inception-resnet and the impact of residual connections on learning, Proc Assoc Adv Artif Intell, 4278
  35. 10.1109/CVPRW.2017.151 · DOI · Paper page
  36. 10.1109/CVPR.2017.298 · DOI · Paper page
  37. 10.1109/ICCV.2017.486 · DOI · Paper page
  38. chen, 0, Dual path networks, Proc Adv Neural Inform Process Syst, 4470
  39. 10.1109/ICCV.2017.514 · DOI · Paper page
  40. 10.1109/CVPR.2018.00262 · DOI · Paper page
  41. 10.1109/ICCV.2015.50 · DOI · Paper page
  42. montufar, 0, On the number of linear regions of deep neural networks, Proc Adv Neural Inf Process Syst, 2924
  43. 10.1109/CVPR.2016.181 · DOI · Paper page
  44. veit, 0, Residual networks behave like ensembles of relatively shallow networks, Proc Adv Neural Inf Process Syst, 550
  45. balduzzi, 0, The shattered gradients problem: If resnets are the answer, then what is the question?, Proc Int Conf Mach Learn, 342
  46. 10.1007/978-3-319-51811-4_29 · DOI
  47. 10.1109/ICCV.2017.198 · DOI · Paper page
  48. 10.1109/CVPRW.2017.150 · DOI · Paper page
  49. 10.1016/j.cviu.2015.09.008 · DOI
  50. 10.1109/ICCV.2001.937655 · DOI · Paper page
  51. 10.1109/CVPR.2018.00344 · DOI · Paper page
  52. 10.1007/978-3-030-01249-6_16 · DOI · Paper page
  53. 10.1109/CVPR.2018.00070 · DOI · Paper page
  54. haris, 0, Deep backprojection networks for super-resolution, Proc Conf Comput Vis Pattern Recognit, 1664
  55. 10.1109/ICCV.2013.121 · DOI · Paper page
  56. 10.1016/j.sigpro.2017.12.017 · DOI
  57. 10.1109/TCI.2016.2644865 · DOI · Paper page
  58. 10.1109/CVPR.2018.00082 · DOI · Paper page
  59. ulyanov, 0, Deep image prior, Proc IEEE Conf Comput Vis Pattern Recognit, 9446
  60. 10.1109/TNNLS.2013.2262001 · DOI
  61. 10.1109/TIP.2018.2875569 · DOI
  62. 10.1109/TASSP.1981.1163711 · DOI · Paper page
  63. 10.1175/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2 · DOI · Paper page
  64. dai, 2009, Softcuts: A soft edge smoothness prior for color image super-resolution, IEEE Trans Image Process, 18, 969, 10.1109/TIP.2009.2012908 · DOI · Paper page
  65. sun, 0, Image super-resolution using gradient profile prior, Proc IEEE Conf Comput Vis Pattern Recognit, 1
  66. yan, 2015, Single image superresolution based on gradient profile sharpness, IEEE Trans Image Process, 24, 3187, 10.1109/TIP.2015.2414877 · DOI · Paper page
  67. 10.1007/s10915-008-9214-8 · DOI · Paper page
  68. 10.1109/38.988747 · DOI · Paper page
  69. 10.1007/978-3-319-54187-7_10 · DOI
  70. 10.1109/CVPR.2004.1315043 · DOI · Paper page
  71. 10.1109/TIP.2016.2564643 · DOI · Paper page
  72. 10.1109/TSP.2006.881199 · DOI · Paper page
  73. 10.1109/CVPR.2017.618 · DOI · Paper page
  74. 10.1109/TIP.2010.2050625 · DOI · Paper page
  75. 10.1109/TIP.2017.2750403 · DOI · Paper page
  76. 10.1007/978-3-319-46475-6_43 · DOI · Paper page
  77. 10.1007/978-3-030-01264-9_47 · DOI · Paper page
  78. gregor, 0, Learning fast approximations of sparse coding, Proc 27th Int Conf Int Conf Mach Learn, 399
  79. 10.1016/1049-9652(91)90045-L · DOI · Paper page
  80. 10.1109/ICCV.2017.481 · DOI · Paper page
  81. 10.1109/CVPRW.2018.00113 · DOI · Paper page
  82. 10.1109/ICCV.2017.581 · DOI
  83. 10.1007/978-3-319-16808-1_37 · DOI
  84. van den oord, 0, Pixel recurrent neural networks, Proc Int Conf Mach Learn, 1747
  85. van den oord, 0, Conditional image generation with PixelCNN decoders, Proc Adv Neural Inf Process Syst, 4790

Cited by

See all 1,154

Metadata

Authors
Yang, W., Zhang, X., Tian, Y., Wang, W., Xue, J.-H., & Liao, Q.
Venue
IEEE Transactions on Multimedia
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2019-12
Volume
21
Issue
12
Pages
3106-3121
ISSN
  • 1520-9210 (ISSN-L)
  • 1941-0077
DOI
10.1109/tmm.2019.2919431
OpenAlex
W2887695188
Cited by
1,154
References
30
FWCI
62.68
Type
journal article
Language
en
Open access
green
Licence
Funders
  • National Natural Science Foundation of China (61471216, 61771276)
  • National Basic Research Program of China (2016YFB0101001)
  • Special Foundation for the Development of Strategic Emerging Industries of Shenzhen (JCYJ20170307153940960, JCYJ20170817161845824)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Deep Learning for Single Image Super-Resolution: A Brief Review. https://app.cochat.ai/papers/10.1109/tmm.2019.2919431
The paper
Yang, W., Zhang, X., Tian, Y., Wang, W., Xue, J.-H., & Liao, Q. (2019). Deep Learning for Single Image Super-Resolution: A Brief Review. IEEE Transactions on Multimedia. https://doi.org/10.1109/tmm.2019.2919431

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.