Super-resolution from a single image
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Methods for super-resolution can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose a unified framework for combining these two families of methods. We further show how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples). Our approach is based on the observation that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution. Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A Review of Image Denoising Algorithms, with a New One
Buades, A., Coll, B., & Morel, J. M. (2005) · Multiscale Modeling & Simulation · doi:10.1137/040616024 · Cited by 4,083 · cited 2×
“Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.”
BackgroundMethodTexture synthesis by non-parametric sampling
Efros, A. A., & Leung, T. K. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790383 · Cited by 3,023
Example-based super-resolution
Freeman, W. T., Jones, T. R., & Pasztor, E. C. (2002) · IEEE Computer Graphics and Applications · doi:10.1109/38.988747 · Cited by 2,498 · cited 5×
“In Fig. 7 we compare our method to results from [ 11 , 13] and [9].”
BackgroundResultInfluentialFast and Robust Multiframe Super Resolution
Farsiu, S., Robinson, M. D., Elad, M., & Milanfar, P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2004.834669 · Cited by 2,090 · cited 2×
“Recurrence of patches within the same image scale forms the basis for applying the Classical SR constraints to information from a single image (Sec.”
MethodImproving resolution by image registration
Irani, M., & Peleg, S. (1991) · CVGIP: Graphical Models and Image Processing · doi:10.1016/1049-9652(91)90045-l · Cited by 1,929 · cited 2×
“Recurrence of patches within the same image scale forms the basis for applying the Classical SR constraints to information from a single image (Sec.”
MethodSelf-citationFreeman, W. T., Pasztor, E. C., & Carmichael, O. T. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026501619075 · Cited by 1,459 · cited 2×
““Example-Based Super-Resolution” also termed “image hallucination” (introduced by [ 10 , 11, 2] and extended later by others e.g.”
BackgroundLimits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1033210 · Cited by 1,205
Limits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854852 · Cited by 1,184 · cited 2×
“Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution.”
InfluentialImage super-resolution using gradient profile prior
Sun, J., Xu, Z., & Shum, H.-Y. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587659 · Cited by 916 · cited 1×
“Sophisticated methods for image up-scaling based on learning edge models have also been proposed (e.g., [9, 19 ]).”
MethodGeneralizing the Nonlocal-Means to Super-Resolution Reconstruction
Protter, M., Elad, M., Takeda, H., & Milanfar, P. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.2008067 · Cited by 707 · cited 1×
“Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.”
Method
Research works printed but not linked: 2
- kim, 8, Example-based learning for single-image SR and JPEG artifact removal, MPI-TR
- efros, 1999, Texture synthesis by nonparametric sampling, ICCV
Cited by
Items 201–300 of 1,002
Blur kernel estimation using normalized color-line priors
Lai, W., Ding, J., Lin, Y., & Chuang, Y. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298601 · Cited by 114
“, 5 × 5 or 7 × 7 image patches) have been developed for image super-resolution [6, 13] and non-blind deconvolution [22, 18].”
BackgroundBest-Buddy GANs for Highly Detailed Image Super-resolution
Li, W., Zhou, K., Qi, L., Lu, L., & Lu, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20030 · Cited by 112
DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-ResolutionPreprint
Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., & Ganguly, A. R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.03126 · Cited by 93
“a scene. „e most successful approaches to SR have been shown to be patch based (or example-based) techniques, achieving state-of-theart performance [10, 35, 39]. Originally proposed by Glasner et al. [14], patch based methods exploit self-similarity between images to produce exemplar patches. „is approach has evolved…”
BackgroundUnified Blind Method for Multi-Image Super-Resolution and Single/Multi-Image Blur Deconvolution
Faramarzi, E., Rajan, D., & Christensen, M. P. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2237915 · Cited by 93
Multidimensional compressed sensing and their applications
Caiafa, C. F., & Cichocki, A. S. (2013) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1108 · Cited by 115
Turning 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
“Single Image Super-Resolution (SISR) [2] [3] [4] [5] [6] [7] [8] [9] is the process of recovering a High-Resolution (HR) image x ∈ R sM×sN from its blurred, decimated, and noisy Low-Resolution (LR) measurement y ∈ R M×N .”
BackgroundUnderwater Image Super-Resolution by Descattering and Fusion
Lu, H., Li, Y., Nakashima, S., Kim, H., & Serikawa, S. (2017) · IEEE Access · doi:10.1109/access.2017.2648845 · Cited by 94
“[19] indicated that after converting a natural image to gray scale, over 90% of the patches of an image have nine or more similar patches at the same scale.”
BackgroundMethodFast Adaptation to Super-Resolution Networks via Meta-learning
Park, S., Yoo, J., Cho, D., Kim, J., & Kim, T. H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58583-9_45 · Cited by 107
Learning Super-Resolution Jointly From External and Internal Examples
Wang, Z., Yang, Y., Wang, Z., Chang, S., Yang, J., & Huang, T. S. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2462113 · Cited by 97
“Internal SR methods search for example patches from the input image itself, based on the fact that patches often tend to recur within the image [13], [14], [11], or across different image scales [5].”
MethodAlternatively Constrained Dictionary Learning For Image Superresolution
Lu, X., Yuan, Y., & Yan, P. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2256347 · Cited by 90
“Image SC SC-NLSS SC-Graph SC-NLSS-Graph The method in [54] The method in [50] The method in [52] The method in [53]”
MethodVFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution
Xie, L., Wang, X., Zhang, H., Dong, C., & Shan, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00081 · Cited by 210
“As a special category of image super-resolution (SR) [12, 14, 30], face super-resolution (FSR) is an active research topic towards face-related applications, and has attracted increasing attention.”
BackgroundDeep Depth Super-Resolution: Learning Depth Super-Resolution Using Deep Convolutional Neural Network
Song, X., Dai, Y., & Qin, X. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54190-7_22 · Cited by 93
“Glasner et al. [19] propose a method searches for similar image patches across multiple down-scaled versions of the image, while the collection of training image data in advance is not needed.”
Xiong, Y., & Zuo, R. (2021) · Mathematical Geosciences · doi:10.1007/s11004-021-09935-z · Cited by 95
“This phenomenon has been reported in existing works (Glasner et al. 2009; Dong et al. 2015; He and Sun 2015), where an improper increase in depth leads to accuracy saturation or classification degradation.”
BackgroundKim, H., Choi, M., Lim, B. O., & Lee, K. M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_25 · Cited by 93
“[7] proposed a novel SR framework that exploits recurrent patches within and across image scales.”
BackgroundDeep Learning Based Single Image Super-resolution: A Survey
Ha, V. K., Ren, J., Xu, X.-Y., Zhao, S. J., Xie, G., Masero, V., & Hussain, A. (2019) · Machine Intelligence Research · doi:10.1007/s11633-019-1183-x · Cited by 99
Video Inpainting With Short-Term Windows: Application to Object Removal and Error Concealment
Ebdelli, M., Meur, O. L., & Guillemot, C. M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2437193 · Cited by 97
“The missing areas can be the result of the removal of one or more undesired objects in the scene [1]–[3].”
Shi, W., Jiang, F., & Zhao, D. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296427 · Cited by 89
“In [4], Glasner feature enhancement layer [7].”
BackgroundA fast blind zero-shot denoiser
Lequyer, J., Philip, R., Sharma, A., Hsu, W.-H., & Pelletier, L. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00547-8 · Cited by 127
“It is also known, and is crucial to some super-resolution methods, that single images have a certain degree of self-similarity, and hence these patches also recur across scales [10, 11].”
BackgroundSpace-Time Super-Resolution Using Graph-Cut Optimization
Mudenagudi, U., Banerjee, S., & Kalra, P. K. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.167 · Cited by 90
Image Super-Resolution Via Double Sparsity Regularized Manifold Learning
Lu, X., Yuan, Y., & Yan, P. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2244798 · Cited by 88
Super-Resolution PET Imaging Using Convolutional Neural Networks
Song, T.-A., Chowdhury, S. R., Yang, F., & Dutta, J. (2020) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2020.2964229 · Cited by 94
“From an applications perspective, we are interested in using this technique to super-resolve PET images of tau tangles, a neuropathological hallmark of Alzheimer’s disease, with the goal of developing sensitive image-based biomarkers for tau [38].”
Wavelet-Based Deep Auto Encoder-Decoder (WDAED)-Based Image Compression
Mishra, D., Singh, S. K., & Singh, R. K. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3010627 · Cited by 101
Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
Yue, Z., Zhao, Q., Xie, J., Zhang, L., Meng, D., & Wong, K.-Y. K. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00217 · Cited by 107
“Most of the existing methods focus on designing more rational image priors, such as gradient profile [43], sparsity [8, 21], DIP [47] and so on [10, 12, 23, 33, 35, 39].”
MethodToward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data
Köhler, T., Bätz, M., Naderi, F., Kaup, A., Maier, A., & Rieß, C. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2917037 · Cited by 110
“Single-image SR (SISR) infers HR details from a low-resolution (LR) image using self-similarities [7], [8] or example data via classical regression [9], [10], [11], [12] or deep learning [13], [14], [15], [16], [17].”
MethodPractical Single-Image Super-Resolution Using Look-Up Table
Jo, Y., & Kim, S. J. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00075 · Cited by 113
“Our methods show faster or comparable runtime compared to bicubic interpolation while achieving much better PSNR quality. or exploit self-similarity from a test image itself [12, 47].”
MethodDeep Learning-Based Single-Image Super-Resolution: A Comprehensive Review
Chauhan, K., Patel, S. N., Kumhar, M., Bhatia, J., Tanwar, S., Davidson, I. E. A., Mazibuko, T. F., & Sharma, R. (2023) · IEEE Access · doi:10.1109/access.2023.3251396 · Cited by 90
“Some models exploit self-similarity within the image to find low and high-resolution patch pairs and thus are self-supervised [12], [13].”
Background1 Adaptive Image Denoising by Targeted DatabasesPreprint
Luo, E., Member, S., Chan, S. H., & Nguyen, T. Q. (2016) · Cited by 81
An Internal Learning Approach to Video Inpainting
Zhang, H., Mai, L., Jin, H., Wang, Z., Xu, N., & Collomosse, J. P. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00281 · Cited by 100
“The translation equivariance of CNN enables DIP to exploit the internal recurrence of visual patterns in images [37], in a similar way as the classical patch-based approaches [19] but with more expressiveness.”
MethodDeep‐learning based super‐resolution for 3D isotropic coronary MR angiography in less than a minute
Küstner, T., Muñoz, C., Psenicny, A., Bustin, A., Fuin, N., Qi, H., Neji, R., Kunze, K., Hajhosseiny, R., Prieto, C., et al. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.28911 · Cited by 85
A Physically Constrained Variational Autoencoder for Geochemical Pattern Recognition
Xiong, Y., Zuo, R., Luo, Z., & Wang, X. (2021) · Mathematical Geosciences · doi:10.1007/s11004-021-09979-1 · Cited by 89
“This phenomenon has been reported in other works (Glasner et al. 2009; Dong et al. 2015; He and Sun ), where an improper increase in depth leads to accuracy saturation or classifi-cation degradation.”
ResultLearning-Based Joint Super-Resolution and Deblocking for a Highly Compressed Image
Kang, L., Hsu, C., Zhuang, B., Lin, C., & Yeh, C. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2434216 · Cited by 82
A Bayesian Nonparametric Approach to Image Super-Resolution
Polatkan, G., Zhou, M., Carin, L., Blei, D. M., & Daubechies, I. C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2321404 · Cited by 87
“[20] provides very sharp edges by artificially enhancing them.”
InfluentialImage reconstruction with locally adaptive sparsity and nonlocal robust regularization
Dong, W., Shi, G., Li, X., Zhang, L., & Wu, X. (2012) · Signal Processing Image Communication · doi:10.1016/j.image.2012.09.003 · Cited by 81
Retrieval Compensated Group Structured Sparsity for Image Super-Resolution
Liu, J., Yang, W., Zhang, X., & Guo, Z. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2614427 · Cited by 82
“Internal SR methods [7], [11]–[15] learn priors from a training set cropped from the LR image itself.”
MethodConvolutional low-resolution fine-grained classification
Cai, D., Chen, K., Qian, Y., & Kämäräinen, J. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.10.020 · Cited by 88
High-resolution single-photon imaging with physics-informed deep learning
Bian, L., Song, H., Peng, L., Chang, X., Yang, X., Horstmeyer, R. W., Ye, L., Zhu, C., Qin, T., Zheng, D., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-41597-9 · Cited by 100
“Besides the extremely low resolution and complex noise model, the single-photon image enhancement task faces a more severe challenge due to its low bit depth that is differentfromtheconventionalimageenhancementtasksonCMOSor CCD acquired images 25 – 28 .”
Image and Video Restorations via Nonlocal Kernel Regression
Zhang, H., Yang, J., Yanning, Z., & Huang, T. S. (2012) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2012.2222375 · Cited by 80
“The improvement comparison could be more impressive if one notices that, in [21], multiple scales are used for similar pattern matching while our method only uses one scale, although our results can be further improved by using multiscale self-similarities [44].”
InfluentialLight Field Super-Resolution via LFBM5D Sparse Coding
Alain, M., & Smolić, A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451162 · Cited by 92
“Single image super-resolution (SISR) is a major research topic in image processing which has lead to very advanced methods [5–15].”
BackgroundImage Super-Resolution via Attention Based Back Projection Networks
Liu, Z.-S., Wang, L., Li, C.-T., Siu, W.-C., & Chan, Y. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00436 · Cited by 79
“It is commonly used in image denoising [6], inpainting [2] and super-resolution [10].”
BackgroundLight Field Super-Resolution via Adaptive Feature Remixing
Ko, K., Koh, Y. J., Chang, S., & Kim, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3069291 · Cited by 84
“Single-Image SR: Extensive researches have been carried out to perform single-image SR, including elementary interpolation [22], [23], self-similarity [24], [25] and dictionary learning [26], [27] methods.”
MethodHow Not to Be Seen — Object Removal from Videos of Crowded Scenes
Granados, M., Tompkin, J., Kim, K., Grau, O., Kautz, J., & Theobalt, C. (2012) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2012.03000.x · Cited by 91
“Fortunately, videos contain a high degree of redundancy, with repetitive patterns occurring at different locations, times, and scales [GBI09].”
BackgroundForeground Gating and Background Refining Network for Surveillance Object Detection
Fu, Z., Chen, Y., Yong, H., Jiang, R., Zhang, L., & Hua, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2922095 · Cited by 82
HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
Zhang, X., Zhang, Y., & Yu, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73661-2_27 · Cited by 156
Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers
Abu-Hussein, S., Tirer, T., & Giryes, R. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00150 · Cited by 88
Image upsampling via texture hallucination
HaCohen, Y., Fattal, R., & Lischinski, D. (2010) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2010.5585097 · Cited by 84
“Recently, Glasner et al. [12] combined this approach with classical multi-image super-resolution that relies on repetitions in the input image itself.”
BackgroundComputed tomography super-resolution using convolutional neural networks
Yu, H., Liu, D., Shi, H., Yu, H., Wang, Z., Wang, X., Cross, B., Bramler, M., & Huang, T. S. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8297022 · Cited by 87
“Learning-based SR algorithms, on the other hand, learn representations from large training databases of HR and LR image pairs [12, 13], exploit selfsimilarities within an image [14], or combine both ways [15].”
BackgroundGenerative Bayesian Image Super Resolution With Natural Image Prior
Zhang, H., Zhang, Y., Li, H., & Huang, T. S. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2199330 · Cited by 81
“Examples are local regularities, such as edges [8] and self-similarities [3], [4].”
BackgroundSingh, A., Porikli, F., & Ahuja, N. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.364 · Cited by 82
“The SR algorithm we use follows the self-similarity principles described in [7, 4].”
BackgroundMethodInfluentialNon-Photorealistic Rendering and the science of art
Hertzmann, A. (2010) · International Symposium on Non-Photorealistic Animation and Rendering (NPAR) · doi:10.1145/1809939.1809957 · Cited by 86
Super Resolution Image Reconstruction Through Bregman Iteration Using Morphologic Regularization
Purkait, P., & Chanda, B. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2201492 · Cited by 82
CCR: Clustering and Collaborative Representation for Fast Single Image Super-Resolution
Zhang, Y., Zhang, Y., Zhang, J., & Dai, Q. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2512046 · Cited by 80
“layer by layer under the notion internal example-based algorithm [43].”
Single Image Super-Resolution Based on Wiener Filter in Similarity Domain
Cruz, C., Mehta, R., Katkovnik, V. Y., & Egiazarian, K. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2779265 · Cited by 80
Conditional Entropy Coding for Efficient Video Compression
Liu, J. T., Wang, S., Ma, W.-C., Shah, M., Hu, R. M., Dhawan, P., & Urtasun, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58520-4_27 · Cited by 74
Blind Super-Resolution via Meta-Learning and Markov Chain Monte Carlo Simulation
Xia, J., Yang, Z., Li, S., Zhang, S., Fu, Y., Gündüz, D., & Li, X. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3400041 · Cited by 87
“Differ to the conventional deep learning methods that focus on optimizing each task exhaustedly, meta-learning methods [18], [19], [20], [21] prefer to leverage the mutual experience of solving different tasks to obtain good generalization-ability and adaptability for the trained model.”
BackgroundA Bayesian Approach to Alignment-Based Image Hallucination
Tappen, M. F., & Liu, C. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33786-4_18 · Cited by 74
“confront the difficult technical problem: How should the example patches be chosen? Systems have used a number of different approaches, including drawing examples on a patch-by-patch basis, as in [5,6], using self-similarity, as in [9], using user-input, as in [8], or recognizing textural-properties, as in [7,10].”
BackgroundComputational Imaging for VLBI Image Reconstruction
Bouman, K. L., Johnson, M. D., Zoran, D., Fish, V. L., Doeleman, S. S., & Freeman, W. T. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.105 · Cited by 106
Incorporating image priors with deep convolutional neural networks for image super-resolution
Liang, Y., Wang, J., Zhou, S., Gong, Y., & Zheng, N. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.02.046 · Cited by 79
“In another evolving and promising line of methodology, the example based approach [4, 5], the recurrence priors between LR and HR image examples are modeled by learning a mapping from internal/external examples [4, 6] or from combined sources [7].”
BackgroundInterest Point Detector and Feature Descriptor Survey
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_6 · Cited by 83
High-Precision Depth Estimation with the 3D LiDAR and Stereo Fusion
Park, K., Kim, S., & Sohn, K. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461048 · Cited by 85
“Early approaches of the non-guided upsampling have leveraged repetitive structures to identify similar patches across different scales [1], [2].”
BackgroundEnd-to-End Alternating Optimization for Real-World Blind Super Resolution
Luo, Z., Huang, Y., Li, S., Wang, L., & Tan, T. N. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01833-7 · Cited by 81
“In Glasner et al. (2009); Shocher et al. (2018); Soh et al. (2020), the blur kernel is used to down sample images and synthesize training samples, which can be used to train a specific model for a given kernel and LR image.”
MethodEfficient Swin Transformer for Remote Sensing Image Super-Resolution
Kang, X., Duan, P., Li, J., & Shutao Li, A. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3489228 · Cited by 71
“Nonlocal priors are that the input images often have much nonlocal redundancy, and the high-resolution image patch is obtained by hunting for similar patches [41], [42] or adding the regularization [43], [44].”
BackgroundWoods, J. (2012) · Elsevier eBooks · doi:10.1016/b978-0-12-381420-3.00011-4 · Cited by 71
Kopf, J., & Lischinski, D. (2011) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/1964921.1964994 · Cited by 71
“In the last decade, many sophisticated algorithms have appeared which make stronger assumptions about the image, e.g., assuming natural image statistics [Fattal 2007] or self-similarity [Glasner et al. 2009].”
BackgroundSingle image super-resolution: a comprehensive review and recent insight
Al‐Mekhlafi, H., & Liu, S. (2023) · Frontiers of Computer Science · doi:10.1007/s11704-023-2588-9 · Cited by 83
Face hallucination based on sparse local-pixel structure
Li, Y., Cai, C., Qiu, G., & Lam, K. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.09.012 · Cited by 70
“The other approach is single-frame SR [6–11], which is also called learning-based SR or example-based SR.”
BackgroundRankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank
Zhang, W., Liu, Y., Dong, C., & Qiao, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3096327 · Cited by 83
“Thanks to the strong learning capability, Convolutional Neural Networks (CNNs) have demonstrated superior performance [1], [2], [3], [4], [5], [6], [7], [8] to the conventional example-based [9], [10], [11], [12], [13] and interpolation-based [14], [15], [16] algorithms.”
BackgroundFeng, X., Zhang, W., Su, X., & Xu, Z. (2021) · Remote Sensing · doi:10.3390/rs13091858 · Cited by 72
Reconstruction of High-Resolution Tongue Volumes From MRI
Woo, J., Murano, E. Z., Stone, M. L., & Prince, J. L. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2012.2218246 · Cited by 68
Blind visual quality assessment for image super-resolution by convolutional neural network
Fang, Y., Zhang, C., Yang, W., Liu, J., & Guo, Z. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5805-z · Cited by 77
“Internal SR methods [6, 11, 12, 75, 77, 87, 91], learn priors from a training set cropped from the LR image itself.”
MethodDeep convolution network for surveillance records super-resolution
Shamsolmoali, P., Zareapoor, M., Jain, D. K., Jain, V. K., & Yang, J. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5915-7 · Cited by 74
“The tricky parts of creating a high-resolution (HR) image from a low-quality image, generally stated as Bsingle image super-resolution^ [8, 13, 40, 42].”
Analyzing Perception-Distortion Tradeoff Using Enhanced Perceptual Super-Resolution Network
Vasu, S., Madam, N. T., & Rajagopalan, A. N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_8 · Cited by 73
High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity
Zhang, M., & Desrosiers, C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2874284 · Cited by 67
Convolutional Neural Network-Based Block Up-Sampling for HEVC
Lin, J., Liu, D., Yang, H., Li, H., & Wu, F. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2884203 · Cited by 75
“[27] for image SR and has later been extended to video [13].”
BackgroundSelf-tuned deep super resolution
Wang, Z., Yang, Y., Wang, Z., Chang, S., Han, W., Yang, J., & Huang, T. S. (2015) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301266 · Cited by 71
SRGAT: Single Image Super-Resolution With Graph Attention Network
Yan, Y., Ren, W., Hu, X., Li, K., Shen, H., & Cao, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3077135 · Cited by 68
“Irani [17] combine the classical and example-based SR by exploiting the patch-recurrence within and across image scales.”
MethodDrop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models
Granot, N., Feinstein, B., Shocher, A., Bagon, S., & Irani, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01310 · Cited by 98
Self-citationHigh-Similarity-Pass Attention for Single Image Super-Resolution
Su, J.-N., Gan, M., Chen, G., Guo, W., & Chen, C. L. P. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3348293 · Cited by 75
“There are many classical self-similarity-based SISR meth-ods [11], [14], [16], [21], [39] that have achieved satisfactory reconstruction results.”
BackgroundInfluentialBasis Prediction Networks for Effective Burst Denoising With Large Kernels
Xia, Z., Perazzi, F., Gharbi, M., Sunkavalli, K., & Chakrabarti, A. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01186 · Cited by 90
Ensemble based deep networks for image super-resolution
Wang, L., Huang, Z., Gong, Y., & Pan, C. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.02.027 · Cited by 68
Active illumination single-pixel camera based on compressive sensing
Magalhães, F., Araujo, F. M. M., Correia, M. V., Abolbashari, M., & Farahi, F. (2011) · Applied Optics · doi:10.1364/ao.50.000405 · Cited by 69
Image Interpolation via Low-Rank Matrix Completion and Recovery
Cao, F., Cai, M., & Tan, Y. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2372351 · Cited by 65
“In [5]–[16], various learning-based methods have been proposed to stabilize the SR ill-posed problem.”
BackgroundMethodSpatially Adaptive Block-Based Super-Resolution
Su, H. Y., Tang, L., Wu, Y., Tretter, D. R., & Zhou, J. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2166971 · Cited by 68
GUN: Gradual Upsampling Network for Single Image Super-Resolution
Zhao, Y., Li, G., Xie, W., Jia, W., Min, H., & Liu, X. (2018) · IEEE Access · doi:10.1109/access.2018.2855127 · Cited by 67
Global Learnable Attention for Single Image Super-Resolution
Su, J.-N., Gan, M., Chen, G., Yin, J.-L., & Chen, C. L. P. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229689 · Cited by 76
“Thus, many self-similarity-based SISR methods [5], [7], [11], [25], [26] were proposed to address the ill-posedness and achieved satisfactory reconstruction results.”
InfluentialGRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
Xiang, J., Yang, J., Deng, Y., & Tong, X. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00209 · Cited by 95
“Image super-resolution Image super-resolution is a longstanding task in computer vision and has seen enormous developments [9, 10, 13, 16, 26, 29, 58, 59, 63, 65].”
BackgroundAdaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Restoration
Fu, Y., Lam, A., Sato, I., & Sato, Y. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0921-6 · Cited by 69
“…patterns, the self-similarity of overlapping patches has been introduced in many papers on topics such as denoising (Buades et al. 2005;Dabov et al. 2007), demosaicing (Buades et al. 2009), super-resolution (Glasner et al. 2009; Yang et al. 2011), and frame rate up-conversion (Shimano et al. 2011).”
BackgroundSingle-Image Super-Resolution via an Iterative Reproducing Kernel Hilbert Space Method
Deng, L.-J., Guo, W., & Huang, T. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2475895 · Cited by 69
“, a frequency technique [3], pixel classification methods [1], [2], iterative back projection methods [11], [34], [39], [57], a hybrid method [14], a kernel regression method [59] and others [5], [9], [22], [53], [62].”
MethodLearning Hierarchical Decision Trees for Single-Image Super-Resolution
Huang, J., & Siu, W.-C. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2513661 · Cited by 66
Zhang, H., Wang, P., & Jiang, Z. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3009224 · Cited by 67
Light Field Super-Resolution using a Low-Rank Prior and Deep Convolutional Neural Networks
Farrugia, R. A., & Guillemot, C. M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2893666 · Cited by 63
“[37]) to ensure that the down sampled version of the super-resolved light field is consistent with the observed low-resolution light field.”
BackgroundSuper-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning
Tirer, T., & Giryes, R. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2920250 · Cited by 64
“Our image-adaptive approach is influenced by the SR approach proposed in [23] that follows the idea of internal recurrence of information inside a single image within and across scales [9, 10, 36].”
BackgroundMethodEndoL2H: Deep Super-Resolution for Capsule Endoscopy
Almalıoğlu, Y., Ozyoruk, K. B., Gökce, A., İncetan, K., Gokceler, G. I., Simsek, M. A., Ararat, K., Chen, R. J., Durr, N. J., Mahmood, F., et al. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3016744 · Cited by 71
Huang, H., & Wu, N. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2163461 · Cited by 64
“, Wang’s [11], Zhuang’s [21], and recently proposed coherent local linear reconstruction (CLLR)-SR [20], Yang’s [23], and Glasner’s [7] algorithms.”
BackgroundMethodDeep Objective Quality Assessment Driven Single Image Super-Resolution
Yan, B., Bare, B., Ma, C., Li, K., & Tan, W. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2914883 · Cited by 66
“Inner-example based SR methods [4]–[6] exploit internal similarities of the same image.”
MethodLearning a Deep Dual Attention Network for Video Super-Resolution
Li, F., Bai, H., & Zhao, Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2972118 · Cited by 69
“Various methods have been proposed to tackle such video SR problem can be divided into two categories: 1) single-frame SR, which mainly comes from single image SR [1]–[5].”
Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling
Trumble, M., Gilbert, A., Hilton, A., & Collomosse, J. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_48 · Cited by 70
Fine-to-coarse knowledge transfer for low-res image classification
Peng, X., Hoffman, J., Yu, S. X., & Saenko, K. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533047 · Cited by 58
“Super-resolution attempts to improve the quality of low resolution images, for example, through the application of cross-scale patch redundancy [5].”
BackgroundZhao, M., Liu, X., Liu, H., & Wong, K. K. L. (2020) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2020.101698 · Cited by 64
Deep learning methods in real-time image super-resolution: a survey
Li, X., Wu, Y., Zhang, W., Wang, R., & Hou, F. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-019-00925-3 · Cited by 70
“[34] propose a scale space pyramid, which can be trained with internal class data, i.”
BackgroundMethodTackling the Ill-Posedness of Super-Resolution through Adaptive Target Generation
Jo, Y., Oh, S. W., Vajda, P., & Kim, S. J. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01597 · Cited by 72
Metadata
- Authors
- Glasner, D., Bagon, S., & Irani, M.
- Affiliations
- Weizmann Institute of Science (IL)
- ORCID
- Bagon, Shai
- Venue
- 2009 IEEE 12th International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2009-09
- Pages
- 349-356
- OpenAlex
- W2534320940
- Cited by
- 1,889
- References
- 20
- Citations by year
- 2026: 15 · 2025: 49 · 2024: 94 · 2023: 113 · 2022: 109 · 2021: 153 · 2020: 162 · 2019: 154 · 2018: 176 · 2017: 154 · 2016: 154 · 2015: 143 · 2014: 139 · 2013: 103 · 2012: 73
- FWCI
- 46.55
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Keywords
- single image super-resolution, multi-frame super-resolution, example-based super-resolution
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.