Blind Image Super-Resolution: A Survey and Beyond
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Blind image super-resolution (SR), aiming to super-resolve low-resolution images with unknown degradation, has attracted increasing attention due to its significance in promoting real-world applications. Many novel and effective solutions have been proposed recently, especially with powerful deep learning techniques. Despite years of efforts, it still remains as a challenging research problem. This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used to solve the SR model. This taxonomy helps summarize and distinguish among existing methods. We hope to provide insights into current research states, as well as revealing novel research directions worth exploring. In addition, we make a summary on commonly used datasets and previous competitions related to blind image SR. Last but not least, a comparison among different methods is provided with detailed analysis on their merits and demerits using both synthetic and real testing images.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216 · cited 3×
“The testing data includes two classic datasets widely used in SR task, namely Set14 [77] and BSD100 [78], and HR images are blurred and downsampled using eight selected isotropic Gaussian kernels for each scale factor to synthesize degraded LR.”
BackgroundAccurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870 · cited 1×
“in image-level [57] or feature-level [58].”
Making a “Completely Blind” Image Quality Analyzer
Mittal, A., Soundararajan, R., & Bovik, A. C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2227726 · Cited by 6,766 · cited 2×
“, NIQE [73]) using reinforcement learning.”
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
Huang, X., & Belongie, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.167 · Cited by 5,076
NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study
Agustsson, E., & Timofte, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.150 · Cited by 4,295
Accelerating the Super-Resolution Convolutional Neural Network
Dong, C., Loy, C. C., & Tang, X. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_25 · Cited by 3,786
Self-citationLearning Deep CNN Denoiser Prior for Image Restoration
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.300 · Cited by 2,116
Second-Order Attention Network for Single Image Super-Resolution
Dai, T., Cai, J., Zhang, Y., Xia, S.-T., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01132 · Cited by 2,010 · cited 1×
“and SR reconstructionmodules, such as introducing residual blocks [58], [59], [60], recursive or recurrent structure [61], [62], attentionmechanism [5], [63], sub-pixel convolution [3], Fig.”
BackgroundSuper-resolution from a single image
Glasner, D., Bagon, S., & Irani, M. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459271 · Cited by 1,889 · cited 2×
“Some others [55], [56] utilize the property of internal self-similarity within a single image without employing external datasets.”
BackgroundNICE: Non-linear Independent Components Estimation
Dinh, L., Krueger, D., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1410.8516 · Cited by 1,493 · cited 1×
“Flow-based kernel prior (FKP) [45] develops a more effective approach for kernel optimization, where a kernel prior in latent space is learned with normalizing flow (NF) [77], [78] technique.”
MethodPlug-and-Play priors for model based reconstruction
Venkatakrishnan, S. V., Bouman, C. A., & Wohlberg, B. (2013) · 2013 IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2013.6737048 · Cited by 1,178
Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and Applications
Chan, S. H., Wang, X., & Elgendy, O. A. (2017) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2016.2629286 · Cited by 904
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Zhang, K., Liang, J., Van Gool, L., & Timofte, R. (2021) · arXiv · doi:10.48550/arxiv.2103.14006 · Cited by 814
Internal statistics of a single natural image
Zontak, M., & Irani, M. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995401 · Cited by 375 · cited 1×
“Nevertheless, its basic assumption [75] may easily fail, especially for natural images with diverse contents (e.”
BackgroundTurning a denoiser into a super-resolver using plug and play priors
Brifman, A., Romano, Y., & Elad, M. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532589 · Cited by 91 · cited 2×
“Specifically, [66] discovers that a denoiser could be adapted to a SISR solver using plug-and-play priors [69].”
Method
Cited by
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Wang, X., Xie, L., Dong, C., & Shan, Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00217 · Cited by 1,684
Self-citationDiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior
Lin, X., He, J., Chen, Z., Lyu, Z., Dai, B., Yu, F., Qiao, Y., Ouyang, W., & Dong, C. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-73202-7_25 · Cited by 266
Self-citationDiffusion Models, Image Super-Resolution, and Everything: A Survey
Moser, B. B., Shanbhag, A. S., Raue, F., Frolov, S., Palacio, S., & Dengel, A. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3476671 · Cited by 117
“The relationship is represented by a degradation mapping where D is a degradation map D : R w × h × c → ¯ w ׯ h × c and contains degradation parameters, including aspects such as blur k , noise n , scaling s , and compression quality q [18].”
Metadata
- Authors
- Liu, A., Liu, Y., Gu, J., Qiao, Y., & Dong, C.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2022
- Volume
- 45
- Issue
- 5
- Pages
- 1-19
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3180712890
- Cited by
- 187
- References
- 19
- FWCI
- 13.92
- Type
- journal article
- Language
- en
- Open access
- green
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.