The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Super-resolution from a single image
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 301–400 of 1,002
Super-Resolution-Based Inpainting
Meur, O. L., & Guillemot, C. M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33783-3_40 · Cited by 60
“Instead of constructing the LR-HR pairs of patches from a set of un-related training images in an external database, the authors in [12] extract these correspondences by searching for matches across different scales of a multi-resolution pyramid constructed from the input lowresolution image.”
BackgroundMethodExample-Based Super-Resolution With Soft Information and Decision
Xiong, Z., Xu, D., Sun, X., & Wu, F. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2264654 · Cited by 60
“So the message from to at the -th iteration can be written as (6)”
BackgroundNAS-DIP: Learning Deep Image Prior with Neural Architecture Search
Chen, Y., Gao, C., Robb, E., & Huang, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58523-5_26 · Cited by 72
Super-resolution via Transform-Invariant Group-Sparse Regularization
Fernandez‐Granda, C., & Candès, E. J. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.414 · Cited by 59
“These example-based methods enforce local consistency to produce sharp-looking edges and are able to hallucinate high-frequency textures very effectively at moderate upsampling factors, especially if prior knowledge about these textures is available [9, 7, 14].”
cellSTORM—Cost-effective super-resolution on a cellphone using dSTORM
Diederich, B., Then, P., Jügler, A., Förster, R., & Heintzmann, R. (2019) · PLoS ONE · doi:10.1371/journal.pone.0209827 · Cited by 59
“A large variety of different network architectures have shown, that, resulting from prior knowledge, single-image super-resolution (interpolation) [42] or recovering the optical phase from an intensity image [43] is possible.”
BackgroundXu, K., Zhang, Z., & Ren, F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_30 · Cited by 70
Single image super-resolution via BM3D sparse coding
Egiazarian, K., & Katkovnik, V. (2015) · 2015 23rd European Signal Processing Conference (EUSIPCO) · doi:10.1109/eusipco.2015.7362905 · Cited by 58
“Internal methods based on image selfsimilarity across the scales have been proposed in [9], [10].”
MethodGuided Frequency Separation Network for Real-World Super-Resolution
Zhou, Y., Deng, W., Tong, T., & Gao, Q. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00222 · Cited by 58
“While there are many classic methods to solve this problem such as [26, 3, 7, 13], the learning-based approaches grow explosively with the advent of deep-learning.”
MethodLAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution
Deng, X., Wang, H., Xu, M., Guo, Y., Song, Y., & Yang, L. (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/cvpr46437.2021.00907 · Cited by 58
“Super-resolution (SR) is a common technique to address the aforementioned issue, which aims to restore an HR image from a single or a sequence of low-resolution (LR) images [12].”
BackgroundCross-View Recurrence-Based Self-Supervised Super-Resolution of Light Field
Sheng, H., Wang, S., Yang, D., Cong, R., Cui, Z., & Chen, R. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3278462 · Cited by 62
“D. SSLB Methods for Super-Resolution 1) SSLB Methods for Single Image Super-Resolution: Glasner et al. [64] utilize the recurrence of patches in the same image to recover the best possible resolution of each pixel.”
BackgroundFast Image Upsampling via the Displacement Field
Wang, L., Wu, H., & Pan, C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2360459 · Cited by 58
“Note that, the LR and HR image patch pairs can be constructed offline from a set of natural images [17]–[20] or online from the input LR image [22], [23].”
Ma, J., Yu, J., Liu, S., Chen, L., Li, X., Feng, J., Chen, Z., Zeng, S., Liu, X., & Cheng, S. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2980839 · Cited by 58
“To further improve the super-resolution effect, learning-based super-resolution methods were developed, including statistical image prior [10], [11], neighbor embedding methods [13], [14], random forest [15], dictionary learning, and sparse representation [16]–[19].”
MethodEdge-Informed Single Image Super-Resolution
Nazeri, K., Thasarathan, H., & Ebrahimi, M. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00409 · Cited by 57
“tistical methods exploit different image properties such as gradient distribution [36] to predict HR images. Patch-based methods use exemplar patches from external datasets [2,11] or the image itself [19,10] to learn mapping functions from LR to HR. Deep Learning-based methods have achieved great performance on SISR u…”
Super-Resolution of Remote Sensing Images via a Dense Residual Generative Adversarial Network
Ma, W., Pan, Z., Yuan, F., & Lei, B. (2019) · Remote Sensing · doi:10.3390/rs11212578 · Cited by 57
“In recent years, due to the powerful learning ability, deep learning (DL) models, especially convolutional neural networks (CNNs), have been widely used to address the ill-posed inverse problem of SR and have demonstrated superiority over reconstruction-based methods [16,17] and other learning paradigms [18,19].”
BackgroundA Variational Pansharpening Method Based on Gradient Sparse Representation
Tian, X. S., Chen, Y., Yang, C., Gao, X., & Ma, J. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3007325 · Cited by 57
“However, the assumption of sparsity is more suitable for patches of the image demonstrating high variance [15].”
BackgroundDual-Camera Super-Resolution with Aligned Attention Modules
Wang, T., Xie, J., Sun, W., Yan, Q., & Chen, Q. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00201 · Cited by 57
“SISR [11] has been actively explored in recent years.”
BackgroundReal-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme
Yang, X., Xiang, W., Zeng, H., & Zhang, L. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00474 · Cited by 108
“There are two major research branches in the field of SR: single image super-resolution (SISR) [9] and video super-resolution (VSR) [1].”
BackgroundDeU-Net 2.0: Enhanced deformable U-Net for 3D cardiac cine MRI segmentation
Dong, S., Pan, Z., Fu, Y., Yang, Q., Gao, Y., Yu, T., Shi, Y., & Zhuo, C. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102389 · Cited by 62
KGSR: A kernel guided network for real-world blind super-resolution
Yan, Q., Niu, A., Wang, C., Ma, X., zhu, Y., Sun, J., & Zhang, Y. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110095 · Cited by 55
FPA-CS: Focal plane array-based compressive imaging in short-wave infrared
Chen, H., Asif, M. S., Sankaranarayanan, A. C., & Veeraraghavan, A. (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.2015.7298849 · Cited by 55
“However, traditional SR cannot arbitrarily increase resolution, and even state-of-the-art SR algorithms are limited to 2–4× upsampling [10].”
BackgroundStatistics for optimal point prediction in natural images
Geisler, W. S., & Perry, J. S. (2011) · Journal of Vision · doi:10.1167/11.12.14 · Cited by 60
Test-Time Training for Out-of-Distribution Generalization
Sun, Y., Wang, X., Liu, Z., Miller, J. J., Efros, A. A., & Hardt, M. (2019) · Cited by 54
Cross Parallax Attention Network for Stereo Image Super-Resolution
Chen, C., Qing, C., Xu, X., & Dickinson, P. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3050092 · Cited by 58
“Before the deep learning era, many classic methods have 91 been proposed to solve the single image super-resolution 92 problem, such as edge-based methods [11], [12], patch-based 93 methods [13]–[15], self-example-learning-based [16], [17], 94 statistics-based methods [18], [19] and sparse-representation- 95 based met…”
MethodUnderstanding Compressive Sensing and Sparse Representation-Based Super-Resolution
Kulkarni, N., Nagesh, P., Gowda, R., & Li, B. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2180773 · Cited by 54
“Single-image SR algorithms have been studied utilizing the patch repetitions across the same scale and multiple scales in natural images [25] and through supervised neighbor embedding algorithms [30].”
MethodCoarse-to-Fine Learning for Single-Image Super-Resolution
Zhang, K., Tao, D., Gao, X., Li, X., & Li, J. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2511069 · Cited by 54
PSyCo: Manifold Span Reduction for Super Resolution
Pérez-Pellitero, E., Salvador, J., Ruiz‐Hidalgo, J., & Rosenhahn, B. (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.2016.203 · Cited by 57
“multi-scale pyramids [10, 22], homographies [12], with the resultant increase in the number of search candidates.”
BackgroundRemote sensing image fusion via compressive sensing
Ghahremani, M., Liu, Y., Yuen, P. W. T., & Behera, A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.04.001 · Cited by 53
“The occurrence of patches across different image scales implicitly provides more appropriate atoms for the patches, thereby the construction of the dictionary can be achieved efficiently even by using a single image without the need of any external database or prior atoms [54].”
BackgroundInfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images
Li, Z., Wang, Q., Snavely, N., & Kanazawa, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19769-7_30 · Cited by 91
Adaptive Transform Domain Image Super-Resolution via Orthogonally Regularized Deep Networks
Guo, T., Mousavi, H. S., & Monga, V. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2913500 · Cited by 55
“In addition to sparse-coding based methods, self-example based methods have demonstrated success by exploring the self-similarity of the patches from the input image itself [8], [35], [36].”
MethodTherISuRNet - A Computationally Efficient Thermal Image Super-Resolution Network
Chudasama, V. M., Patel, H., Prajapati, K., Upla, K. P., Ramachandra, R., Raja, K. B., & Busch, C. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00051 · Cited by 53
“A set of traditional SR works have employed the concept of patch based self-similarity from LR and HR images pairs [10].”
MethodMsLRR: A Unified Multiscale Low-Rank Representation for Image Segmentation
Liu, X., Xu, Q., Ma, J., Jin, H., & Zhang, Y. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2297027 · Cited by 51
“, texture synthesis [8], denoising [3], and super-resolution [10].”
BackgroundBenchmarking Ultra-High-Definition Image Super-resolution
Zhang, K., Li, D., Luo, W., Ren, W., Stenger, B., Liu, W., Li, H., & Yang, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01450 · Cited by 51
“To tackle this problem, traditional methods use prior cues from HR images or LR exemplar images [14, 12, 46, 13, 6, 22, 47, 11, 18, 37, 31].”
MethodAny-Resolution Training for High-Resolution Image Synthesis
Chai, L., Gharbi, M., Shechtman, E., Isola, P., & Zhang, R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19787-1_10 · Cited by 100
Utilizing Image Scales Towards Totally Training Free Blind Image Quality Assessment
Saha, A., & Wu, Q. M. J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2411436 · Cited by 54
“individual image has been statistically demonstrated and used for super-resolution in [4].”
MethodMetric Learning Based Interactive Modulation for Real-World Super-Resolution
Mou, C., Wu, Y., Wang, X., Dong, C., Zhang, J., & Shan, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19790-1_43 · Cited by 73
Single-Image Super-Resolution Using Active-Sampling Gaussian Process Regression
Wang, H., Gao, X., Zhang, K., & Li, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2512104 · Cited by 50
Kopf, J., & Lischinski, D. (2011) · ACM Transactions on Graphics · doi:10.1145/2010324.1964994 · Cited by 50
Prajapati, K., Chudasama, V. M., Patel, H., Upla, K. P., Ramachandra, R., Raja, K. B., & Busch, C. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00240 · Cited by 49
“A number of traditional SR methods [13, 38, 18, 10, 27, 49] have been proposed after first SR approach introduced by Tsai and Huang [46].”
MethodSimilarity-Aware Patchwork Assembly for Depth Image Super-resolution
Li, J., Lu, Z., Zeng, G., Gan, R., & Zha, H. (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.2014.431 · Cited by 49
“[7] combined multi-image-based methods with example-based methods and used redundant information from repeating patches to reconstruct a high resolution image.”
MethodAdaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising
Fu, Y., Lam, A., Sato, I., & Sato, Y. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.47 · Cited by 49
“In addition, due to natural images containing self-repeating patterns, the concept of non-local self-similarity in images is introduced in many papers on topics such as denoising [14, 15], demo-saicing [16], super-resolution[17, 18], and frame rate up-conversion [19].”
BackgroundConvolutional neural networks for wavelet domain super resolution
Kumar, N., Verma, R., & Sethi, A. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.03.014 · Cited by 50
“Learning-based techniques such as Glasner et al. (2009); Zontak and Irani (2011); Sethi et al. (2012); Peleg and Elad (2014); Freeman et al. (2002); Yang et al. (2010); Dong et al. (2015), which are also known as example-based super resolution, have successfully surpassed other techniques, such as…”
MethodDeep Learning Based Single Image Super-Resolution: A Survey
Ha, V. K., Ren, J., Xu, X., Zhao, S. J., Xie, G., & Masero, V. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00563-4_11 · Cited by 61
A multi-image super-resolution algorithm applied to thermal imagery
Mandanici, E., Tavasci, L., Corsini, F., & Gandolfi, S. (2019) · Applied Geomatics · doi:10.1007/s12518-019-00253-y · Cited by 53
“Single-image methods operate almost exclusively in the spatial domain and often implement hallucination algorithms (Baker and Kanade 2002) based on machine learning techniques, which require sets of LR and HR pairs as training (Glasner et al. 2009).”
BackgroundSRPGAN: Perceptual Generative Adversarial Network for Single Image Super ResolutionPreprint
Wu, B., Duan, H., Liu, Z., & Sun, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.05927 · Cited by 49
“It has been a very attractive research topic over the last two decades [7] [1] [8].”
BackgroundSingle-image super-resolution based on Markov random field and contourlet transform
Wu, W., Liu, Z., Gueaieb, W., & He, X. (2011) · Journal of Electronic Imaging · doi:10.1117/1.3580750 · Cited by 48
CodingFlow: Enable Video Coding for Video Stabilization
Liu, S., Li, M., Zhu, S., & Zeng, B. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2697759 · Cited by 52
“in 3D reconstruction [36], image super-resolution [37], and”
BackgroundHigh-resolution bathymetry by deep-learning-based image superresolution
Sonogashira, M., Shonai, M., & Iiyama, M. (2020) · PLoS ONE · doi:10.1371/journal.pone.0235487 · Cited by 48
“An alternative approach is single-image superresolution [4], which uses only a single low-resolution image and exploits prior knowledge regarding a targeted image domain (typically, natural images such as photographs) to recover high-frequency details.”
Backgrounds-LWSR: Super Lightweight Super-Resolution Network
Li, B., Wang, B., Liu, J., Qi, Z., & Shi, Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3014953 · Cited by 48
“RECOVERING a high-resolution (HR) image from its low-resolution (LR) counterpart is a longstanding problem in the image processing regime [1]–[4].”
BackgroundLow-Rank Neighbor Embedding for Single Image Super-Resolution
Chen, X., & Qi, C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2286417 · Cited by 47
“Moreover, the self-learning approaches [15] have been widely studied in recent years because it does not need to collect or select the training set additionally.”
BackgroundLee, J., Cho, S.-H., & Kim, M. (2024) · ETRI Journal · doi:10.4218/etrij.2023-0275 · Cited by 53
“sentations, our global context exploitation further improves the coding efficiency by removing the remaining spatial correlations across a wider area of each input image, motivated by the known wisdom [8,14] that self-similarity exists in the natural images. Fig.1compares the reconstructed sample images of our final mod…”
MethodA Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution
Yang, Z., Xia, J., Li, S., Huang, X., Zhang, S., Liu, Z., Fu, Y., & Liu, Y. (2024) · 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/cvpr52733.2024.02461 · Cited by 67
“To alleviate the non-convexity and ill-posedness, early model-based approaches [11, 31, 33, 37] typically construct image priors in explicit formulations, such as the total variation (TV) [36], gradient profile [42], hyper-Laplacian [21] and sparsity [19].”
Super resolution reconstruction of μ -CT image of rock sample using neighbour embedding algorithm
Wang, Y., Rahman, S. S., & Arns, C. H. (2017) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2017.10.022 · Cited by 46
Image Superresolution via Dense Discriminative Network
Ma, J., Wang, X., & Jiang, J. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2934071 · Cited by 46
“Several methods [20]–[22] for SR utilize the self-similarity property of the natural image and erect scale-space pyramid of the input image for LR–HR matching pairs.”
MethodScene-Adaptive Video Frame Interpolation via Meta-Learning
Choi, M., Choi, J., Baik, S., Kim, T. H., & Lee, K. M. (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/cvpr42600.2020.00946 · Cited by 47
Super-Resolution Using Sub-Band Self-Similarity
Singh, A., & Ahuja, N. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16808-1_37 · Cited by 46
“Kangaroo (3X): Both Glasner [6] and Freedman [11] almost completely lose the textural details of the kangaroo’s tail.”
BackgroundMethodResultInfluentialRethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
Qian, G., Wang, Y., Gu, J., Dong, C., Heidrich, W., Ghanem, B., & Ren, J. (2022) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccp54855.2022.9887682 · Cited by 89
“Previously, example-based SR methods [30], [31] that exploit the self-similarity property provided state-of-the-art performance.”
MethodGou, S., Liu, S., Yang, S., & Jiao, L. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2328596 · Cited by 45
Fast Learning-Based Single Image Super-Resolution
Kumar, N., & Sethi, A. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2571625 · Cited by 45
“matches found has also been proposed [6], [7].”
BackgroundSERF: A Simple, Effective, Robust, and Fast Image Super-Resolver From Cascaded Linear Regression
Hu, Y., Wang, N., Tao, D., Gao, X., & Li, X. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2580942 · Cited by 47
Single Image Super-Resolution Using Global Regression Based on Multiple Local Linear Mappings
Choi, J.-S., & Kim, M. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2651411 · Cited by 45
“We now compare the proposed GLM-SI and OLM-SI with the conventional SR methods, such as bicubic interpolation, SCSR [4], Glasner [26], ANR [5], APLUS [6], SRCNN14 [7], SRCNN15 [8], JOR [9], SI [10] and ARF L [43] methods.”
BackgroundMethodInfluentialDeep Learning for Isotropic Super-Resolution from Non-isotropic 3D Electron Microscopy
Heinrich, L., Bogovic, J., & Saalfeld, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66185-8_16 · Cited by 49
“Methods for SR that take advantage of self-similarity have seen great success and do not require high-resolution examples from which to learn [5].”
BackgroundUnified Single-Image and Video Super-Resolution via Denoising Algorithms
Brifman, A., Romano, Y., & Elad, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2924173 · Cited by 47
“Commonly chosen priors are based on sparse representations [1]–[5], spatial smoothness such as Total Variation [6], self-similarity [7]–[9], and more.”
BackgroundHu, G., Cui, B., & Yu, S. P. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00212 · Cited by 45
“Block-matching is widely used in computer vision tasks like super-resolution (Glasner, Bagon, and Irani 2009), image denoising (Lefkimmiatis 2017).”
MethodJoint Learning in the Spatio-Temporal and Frequency Domains for Skeleton-Based Action Recognition
Hu, G., Cui, B., & Yu, S. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2953325 · Cited by 48
“Blockmatching is widely used in computer vision tasks like superresolution [36], image inpainting [37], image denoising [38] etc.”
Background3DSRnet: Video Super-resolution using 3D Convolutional Neural NetworksPreprint
Kim, S. Y., Lim, J., Na, T., & Kim, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.09079 · Cited by 45
“Past attempts to tackle this problem include internal and external example-based methods [4, 5, 6, 7, 8].”
BackgroundDual Learning-Based Graph Neural Network for Remote Sensing Image Super-Resolution
Liu, Z., Feng, R., Wang, L., Han, W., & Zeng, T. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3199750 · Cited by 54
“See https://www.ieee.org/publications/rights/index.html for more information. patches within a single image, which is widely employed in some early SR methods [21], [22].”
MethodIRE: Improved Image Super-Resolution Based on Real-ESRGAN
Zhu, Z., Lei, Y., Qin, Y., Zhu, C., & Zhu, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3256086 · Cited by 44
“Image SR, a technique based on deep learning, involves converting low-resolution (LR) images into high-resolution (HR) images using specific algorithms [1], [2], [3].”
MethodChang, C., Peng, J., Safari, M., Salari, E., Pan, S., Roper, J. R., Qiu, R. L. J., Gao, Y., Shu, H. G., Mao, H. Z., et al. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad209c · Cited by 58
Depth Super-Resolution From RGB-D Pairs With Transform and Spatial Domain Regularization
Jiang, Z., Hou, Y., Yue, H., Yang, J., & Hou, C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2806089 · Cited by 44
Fast Single Image Super-Resolution Via Dilated Residual Networks
Zhang, L., Zhang, Y., Yali, P., Shigang, L., Wu, X., Lü, G., & Yuan, R. (2018) · IEEE Access · doi:10.1109/access.2018.2865613 · Cited by 44
“The reconstruction-based methods utilize statistical image priors [11], [12] or internal patch recurrence [13].”
MethodFAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos
Zhang, Z., & Sze, V. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.138 · Cited by 44
“There are also SR algorithms that exploit the self-similarities of blocks within each image [18, 19].”
BackgroundJanssens, N., Huysmans, M., & Swennen, R. (2020) · Materials · doi:10.3390/ma13061397 · Cited by 45
Blind Image Super-Resolution via Contrastive Representation LearningPreprint
Zhang, J., Lu, S., Zhan, F., & Yu, Y. (2021) · arXiv (Cornell University) · doi:10.13140/rg.2.2.35795.30248 · Cited by 62
Ground Truth Data, Content, Metrics, and Analysis
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_7 · Cited by 52
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
Wang, Y., Su, T., Li, Y., Cao, J., Wang, G., & Liu, X. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3219646 · Cited by 48
“S UPER-RESOLUTION (SR) is a classic computer vision problem, which aims to restore a high-resolution image from its degraded low-resolution counterpart [1].”
BackgroundRevealing and modifying non-local variations in a single image
Dekel, T., Michaeli, T., Irani, M., & Freeman, W. T. (2015) · ACM Transactions on Graphics · doi:10.1145/2816795.2818113 · Cited by 43
“, 5 × 5) were shown to recur abundantly in almost any natural image [Glasner et al. 2009], these recurrences relate to tiny structures (e.”
BackgroundSelf-citationFast Image Super-Resolution via Local Adaptive Gradient Field Sharpening Transform
Song, Q., Xiong, R., Liu, D., Xiong, Z., Wu, F., & Gao, W. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2789323 · Cited by 43
“To reduce dependence on training images, self-example approaches exploit the fact that patches of similar pattern tend to recur inside an image itself as well as across different scales [28]–[32].”
BackgroundDeep learning enhancement of infrared face images using generative adversarial networks
Guei, A., & Akhloufi, M. A. (2018) · Applied Optics · doi:10.1364/ao.57.000d98 · Cited by 47
Medical Image Imputation From Image Collections
Dalca, A. V., Bouman, K. L., Freeman, W. T., Rost, N. S., Sabuncu, M. R., & Golland, P. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2866692 · Cited by 46
Dense Bynet: Residual Dense Network for Image Super Resolution
Xu, J., Chae, Y., Stenger, B., & Datta, A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451696 · Cited by 43
“Methods including self-similarity [1, 2], sparse coding [3, 4], and neighborhood embedding [5, 6] have been applied to learn the nonlinear mapping.”
MethodEnhancing OCR Accuracy with Super Resolution
Lat, A., & Jawahar, C. V. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545609 · Cited by 43
“After converting, training is done only on the L component [13] while a and b components are up-scaled using standard interpolation.”
MethodAdaptive Importance Learning for Improving Lightweight Image Super-Resolution Network
Zhang, L., Wang, P., Shen, C., Liu, L., Wei, W., Zhang, Y., & van den Hengel, A. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01253-6 · Cited by 44
“Different from these methods, Glasner et al. (Glasner et al, 2009) propose to exploit the internal patch recurrence for super-resolution.”
MethodDharejo, F. A., Deeba, F., Zhou, Y., Das, B., Jatoi, M. A., Zawish, M., Du, Y., & Wang, X. (2021) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3456726 · Cited by 43
“Due to their good learning ability, DL-based methods have also been used to solve SR-based inverse problems, and the discovery of non-DL-based SR methods has been enhanced [16][41][11][58].”
MethodSuper-Resolution Images Methodology Applied to UAV Datasets to Road Pavement Monitoring
Inzerillo, L., Acuto, F., Mino, G. D., & Uddin, M. Z. (2022) · Drones · doi:10.3390/drones6070171 · Cited by 47
“Among them, the examplebased methods [20] achieved the state-of-the-art performance.”
MethodInformation-Growth Attention Network for Image Super-Resolution
Li, Z., Li, G., Li, T., Liu, S., & Gao, W. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475207 · Cited by 42
“Conventional image super-resolution techniques can be roughly divided into two varieties named by external example-based approaches [21, 43, 49, 49] and internal example-based approaches [4, 9, 10, 51].”
BackgroundHallucinating Unaligned Face Images by Multiscale Transformative Discriminative Networks
Yu, X., Porikli, F., Fernando, B., & Hartley, R. I. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01254-5 · Cited by 42
“Glasner et al. (2009), Freedman and Fattal (2010), Singh et al. (2014) and Huang et al. (2015) exploit self-similarity of patches in an input image to generate HR patches.”
BackgroundDeep learning for camera data acquisition, control, and image estimation
Brady, D. J., Fang, L., & Ma, Z. (2020) · Advances in Optics and Photonics · doi:10.1364/aop.398263 · Cited by 50
Deep CNN-Based Super-Resolution Using External and Internal Examples
Cheong, J. Y., & Park, I. K. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2721104 · Cited by 41
“We use the results of [15], [16], and [18] from Huang et al. ’s webpage [28] as benchmark.”
MethodInfluentialVideo Super-Resolution Using Non-Simultaneous Fully Recurrent Convolutional Network
Li, D., Liu, Y., & Wang, Z. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2877334 · Cited by 43
Component Attention Guided Face Super-Resolution Network: CAGFace
Kalarot, R., Li, T., & Porikli, F. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093399 · Cited by 52
“This task has been one of the most fundamental challenges in computer vision, and many approaches have been proposed within the last two decades including kernel interpolations [31], edge statistics [13, 46], patch-based schemes [15, 52, 22, 14, 62, 61, 21, 41], Bayesian methods [47, 26, 43], and supervised”
MethodSingular value decomposition based fusion for super-resolution image reconstruction
Nasir, H., Stanković, V., & Marshall, S. (2011) · Signal Processing Image Communication · doi:10.1016/j.image.2011.12.002 · Cited by 47
“, [1-5]) require a large amount of training data to generate efficient learning models, while multi-image/frame super-resolution methods involved an illposed inverse problem with matrices of very large dimensions.”
BackgroundA Convex Approach for Variational Super-Resolution
Unger, M., Pock, T., Werlberger, M., & Bischof, H. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15986-2_32 · Cited by 40
“A similar approach is taken by Glasner et al. in [5], where patch redundancy over various scales of a single image is used to signifi-cantly improve zooming for pictures with redundant structures.”
MethodSingle Image Super Resolution using a Joint GMM Method
Sandeep, P., & Jacob, T. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2588319 · Cited by 40
“Another recent approach in learning based SR is self example based methods that exploit the self recurring nature of image structures such as patches within and across different scales [36]–[39].”
BackgroundImage Interpolation Based on Non-local Geometric Similarities and Directional Gradients
Zhu, S., Zeng, B., Zeng, L., & Gabbouj, M. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2593039 · Cited by 40
“It is important to point out that our work is different from the traditional example-based image super-resolution (SR) strategy, such as [17], [18].”
Light Field Super-Resolution Using Edge-Preserved Graph-Based Regularization
Ghassab, V. K., & Bouguila, N. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2946094 · Cited by 40
Prajapati, K., Chudasama, V. M., Patel, H., Upla, K. P., Raja, K. B., Ramachandra, R., & Busch, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3113783 · Cited by 45
Residual Skip Network-Based Super-Resolution for Leaf Disease Detection of Grape Plant
Yeswanth, P. V., Deivalakshmi, S., George, S., & Ko, S. (2023) · Circuits Systems and Signal Processing · doi:10.1007/s00034-023-02430-2 · Cited by 44
“Several patch replacement techniques [9, 18, 22, 27] addressed the problem of sharp edge blurring in interpolation-based methods.”
BackgroundMRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and BetterPreprint
Chen, Y., Christodoulou, A., Zhou, Z., Shi, F., Xie, Y., & Li, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01217 · Cited by 55
“Therefore, with the capability to restore resolution loss in HR from just a single LR image, Singe Image Super-Resolution (SISR) (Glasner et al., 2009) is an appealing approach as it promises a reconstructed HR image without adding extra scans or additional multi-image combination processing.”
BackgroundMulti-shot Imaging: Joint Alignment, Deblurring, and Resolution-Enhancement
Zhang, H., & Carin, L. (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.2014.374 · Cited by 39
“[6] and performs similar to Michaeli and Irani’s recent method [14], both of which incorporated the multiscale self-similarity image prior.”
MethodCrossNet++: Cross-Scale Large-Parallax Warping for Reference-Based Super-Resolution
Tan, Y., Zheng, H., Zhu, Y., Yuan, X., Lin, X., Brady, D. J., & Fang, L. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2997007 · Cited by 43
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.