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 101–200 of 1,002
Blind Image Super-Resolution: A Survey and Beyond
Liu, A., Liu, Y., Gu, J., Qiao, Y., & Dong, C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3203009 · Cited by 187
“Some others [55], [56] utilize the property of internal self-similarity within a single image without employing external datasets.”
BackgroundLearning Multiple Linear Mappings for Efficient Single Image Super-Resolution
Zhang, K., Tao, D., Gao, X., Li, X., & Xiong, Z. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2389629 · Cited by 195
“Unlike the aforementioned methods that rely on an external training dataset, several state-of-art approaches to SR have recently been developed that exploit the self-similarity of structures in the LR input [28]–[30].”
MethodExploiting Self-similarities for Single Frame Super-Resolution
Yang, C.-Y., Huang, J.-B., & Yang, M.-H. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-19318-7_39 · Cited by 190
“and implement the algorithm of [12](1).”
BackgroundMethodInfluentialA survey of deep learning approaches to image restoration
Su, J., Xu, B., & Yin, H. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.02.046 · Cited by 181
Statistics of Patch Offsets for Image Completion
He, K., & Sun, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33709-3_2 · Cited by 187
“Gradient-domain statistics have been applied in denoising [29], deconvolution [30], and inpainting [3], whereas recent patch-domain statistics have been shown very successful in denoising [29] and super-resolution [31].”
A New Deep Generative Network for Unsupervised Remote Sensing Single-Image Super-Resolution
Haut, J. M., Fernandez-Beltran, R., Paoletti, M. E., Plaza, J., Plaza, A., & Pla, F. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2843525 · Cited by 186
“For example, the work presented in [64] approximates the blur operator by a Gaussian kernel, and the patch redundancy process is conducted by an approximation of the nearest neighbor search.”
MethodEnhancing Hi-C data resolution with deep convolutional neural network HiCPlus
Zhang, Y., An, L., Xu, J., Zhang, B., Zheng, W. J., Hu, M., Tang, J., & Yue, F. (2018) · Nature Communications · doi:10.1038/s41467-018-03113-2 · Cited by 188
“Our approach is inspired by the most recent advancements 27 – 30 in the single image super-resolution and can generate the Hi-C interaction matrices with the similar quality as the original ones, while using as few as 1/16 of sequencing reads.”
MethodSuper-resolution analysis via machine learning: a survey for fluid flows
Fukami, K., Fukagata, K., & Taira, K. (2023) · Theoretical and Computational Fluid Dynamics · doi:10.1007/s00162-023-00663-0 · Cited by 176
“This problem set has been traditionally tackled in computer visions with various techniques including interpolation [4, 5, 6, 7], example-based internal learning [8, 9, 10, 11], high-frequency transfer [12, 13, 14, 15], neighbor embedding [16, 17, 18, 19, 20], and sparse coding [21, 22, 23, 24, 25].”
MethodHybrid-Scale Self-Similarity Exploitation for Remote Sensing Image Super-Resolution
Lei, S., & Shi, Z. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3069889 · Cited by 173
“Local image patterns tend to redundantly recur in the image with similar contours and textures [28], [33].”
BackgroundDeep Video Super-Resolution Using HR Optical Flow Estimation
Wang, L., Guo, Y., Liu, L., Lin, Z., Deng, X., & An, W. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967596 · Cited by 176
Huang, D.-A., & Wang, Y.-C. F. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.310 · Cited by 175
“For the method of [6], we apply the code implemented by Yang et al.”
BackgroundMethodA comprehensive review of deep learning-based single image super-resolution
Bashir, S. M. A., Wang, Y., Khan, M., & Niu, Y. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.621 · Cited by 172
RetractedImage Completion Approaches Using the Statistics of Similar Patches
He, K., & Sun, J. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2330611 · Cited by 172
Through Fog High-Resolution Imaging Using Millimeter Wave Radar
Guan, J., Madani, S., Jog, S., Gupta, S., & Hassanieh, H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01148 · Cited by 168
“Super-Resolution: Neural networks have been used to increase the resolution of camera images and near-Infrared images [28, 32, 38, 40].”
MethodUnsupervised Real-world Image Super Resolution via Domain-distance Aware Training
Wei, Y., Gu, S., Li, Y., Timofte, R., Jin, L., & Song, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01318 · Cited by 161
Flow-based Kernel Prior with Application to Blind Super-Resolution
Liang, J., Zhang, K., Gu, S., Gool, L. V., & Timofte, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01046 · Cited by 160
“In a single image, small image patches tend to recur across different scales [16, 57].”
BackgroundMethodCross-Scale Internal Graph Neural Network for Image Super-ResolutionPreprint
Zhou, S., Zhang, J., Zuo, W., & Loy, C. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.16673 · Cited by 299
“Our IGNN is based on cross-scale patch recurrence property verified statistically in [45, 9, 28] that patches in a single natural image tend to recur many times across scales.”
BackgroundMethodInfluentialEdge-Directed Single-Image Super-Resolution Via Adaptive Gradient Magnitude Self-Interpolation
Wang, L., Xiang, S., Meng, G., Wu, H., & Pan, C. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2240915 · Cited by 163
Joint Learning for Single-Image Super-Resolution via a Coupled Constraint
Gao, X., Zhang, K., Tao, D., & Li, X. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2161482 · Cited by 163
Lu, E., Xie, W., & Zisserman, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_42 · Cited by 210
MuCAN: Multi-correspondence Aggregation Network for Video Super-Resolution
Li, W., Tao, X., Guo, T., Qi, L., Lu, J., & Jia, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58607-2_20 · Cited by 226
Jointly Optimized Regressors for Image Super‐resolution
Dai, D., Timofte, R., & Van Gool, L. (2015) · Computer Graphics Forum · doi:10.1111/cgf.12544 · Cited by 158
Is image super-resolution helpful for other vision tasks?
Dai, D., Wang, Y., Chen, Y., & Gool, L. V. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477613 · Cited by 177
“Methods [12, 14, 43, 17] in the former stream draw on the ‘self-similarity’ of images across scales, and have obtained great success.”
BackgroundBhat, G., Danelljan, M., Gool, L. V., & Timofte, R. (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/cvpr46437.2021.00909 · Cited by 212
“Single Image Super-Resolution: SISR is a widely studied task with a variety of proposed methods, for example based on the frequency domain [34, 19, 36], interpolation techniques [16, 5, 25], sparse representations [47, 28, 46] or patch and examples [4, 11, 13].”
BackgroundSuper-resolution from internet-scale scene matching
Sun, L., & Hays, J. H. (2012) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2012.6215221 · Cited by 181
“We compare our algorithm against two recent meth-ods which we consider exemplary of the state-of-the-art in super-resolution – [31] uses segment-level matching to a database of thousands of images, and [11] uses internal image statistics.”
BackgroundMethodResultInfluentialSingle Image Superresolution Based on Gradient Profile Sharpness
Yan, Q., Xu, Y., Yang, X., & Nguyen, T. Q. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2414877 · Cited by 158
“The proposed method is compared with more state-of-the-art super-resolution methods, which include one interpolation-based method (ICBI11 [6]), three reconstruction-based methods (Fattal07 [27], Shan08 [32] and Sun11 [31]), four learning-based methods (Freeman02 [7], Glasner09 [13] and Freedman11 [14], BPJDL13 [17]),…”
MethodInfluentialATGV-Net: Accurate Depth Super-Resolution
Riegler, G., Rüther, M., & Bischof, H. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_17 · Cited by 170
InGAN: Capturing and Retargeting the “DNA” of a Natural Image
Shocher, A., Bagon, S., Isola, P., & Irani, M. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00459 · Cited by 185
“, 5x5, 7x7) recur abundantly inside a single natural image [13, 33].”
BackgroundSelf-citationLearning to Remove Soft Shadows
Gryka, M., Terry, M. A., & Brostow, G. (2015) · ACM Transactions on Graphics · doi:10.1145/2732407 · Cited by 154
“Therefore, we have used automatically segmented silhouettes of real objects from Griffin et al. [2007] as occluders in our synthetic scenes (we have segmented them automatically by using Boykov et al.”
BackgroundMethodNovel Example-Based Method for Super-Resolution and Denoising of Medical Images
Trinh, D. H., Luong, M., Dibos, F., Rocchisani, J.-M., Pham, C. D., & Nguyen, T. Q. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2308422 · Cited by 154
“categorized into two main groups: multi-image SR [15]–[18] and single-image SR [19]–[33].”
BackgroundEnhancing the Spatial Resolution of Stereo Images Using a Parallax Prior
Jeon, D. S., Baek, S.-H., Choi, I., & Kim, M. H. (2018) · 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.2018.00185 · Cited by 170
“Recent advances in enhancing spatial resolution have recovered a highresolution image from a single source image itself by finding similar small patches [20, 52, 24, 53, 36, 43], joint learning [15, 8], or convolutional neural networks [13, 53, 9].”
BackgroundWang, X., Girshick, R., Gupta, A., & He, K. (2017) · arXiv · Cited by 11,689
“Non-local matching is also the essence of successful texture synthesis [12], super-resolution [16], and inpainting [1] algorithms.”
BackgroundA Deep Convolutional Neural Network with Selection Units for Super-Resolution
Choi, J.-S., & Kim, M. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.153 · Cited by 160
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
Liu, A., Makadia, A., Tucker, R., Snavely, N., Jampani, V., & Kanazawa, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01419 · Cited by 141
“Our problem also incorporates aspects of super-resolution [14, 22].”
BackgroundEnd-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks
Wang, Y., Wang, L., Wang, H., & Li, P. (2019) · IEEE Access · doi:10.1109/access.2019.2903582 · Cited by 143
Pan, Z., Yu, J. S., Huang, H., Hu, S., Zhang, A., Ma, H., & Sun, W. (2013) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2012.2230270 · Cited by 146
“As a solution to the aforementioned problems, structural similarity-based SR methods [21], [22] solve the SR problem by using only the LR image itself instead of the database.”
BackgroundMethodInfluentialSingle Image Super-Resolution With Multiscale Similarity Learning
Zhang, K., Gao, X., Tao, D., & Li, X. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2262001 · Cited by 142
“In particular, Glasner et al. [30] proposed an SR approach by combining the traditional multiimagebased and example learning-based SR methods, in which cross-scale patch redundancy is employed to form an example learning-based method for detail hallucination.”
BackgroundMethodInfluentialDeep-Learning-Based Image Reconstruction and Enhancement in Optical Microscopy
Haan, K. D., Rivenson, Y., Wu, Y., & Özcan, A. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2949575 · Cited by 158
“[22] D.”
Super resolution techniques for medical image processing
Isaac, J. S., & Kulkarni, R. K. (2015) · International Conference on Technologies for Sustainable Development (ICTSD) · doi:10.1109/ictsd.2015.7095900 · Cited by 135
Geometry-Consistent Light Field Super-Resolution via Graph-Based Regularization
Rossi, M., & Frossard, P. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2828983 · Cited by 147
“This goal is typically achieved by learning a mapping from the low resolution data to the high resolution one, either on an external training set [8] [9] [10] or on the image itself [11] [12].”
BackgroundImage Transformation Based on Learning Dictionaries across Image Spaces
Jia, K., Wang, X., & Tang, X. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.95 · Cited by 136
“From left to right: Bicubic interpolation, results from [21], our final results.”
MethodResultFast Single Image Super-Resolution via Self-Example Learning and Sparse Representation
Zhu, Z., Guo, F., Yu, H., & Chen, C. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2364976 · Cited by 139
“The basic prior used in [19] is that numerous similar image patches exist in most natural images.”
BackgroundLearning to Incorporate Structure Knowledge for Image Inpainting
Yang, J., Qi, Z., & Shi, Y. G. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6951 · Cited by 158
Scene-Adaptive Remote Sensing Image Super-Resolution Using a Multiscale Attention Network
Shu, Z., Yuan, Q., Li, J., Sun, J., & Zhang, X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2966805 · Cited by 142
“S INGLE-IMAGE super-resolution (SISR) is a low-level computer vision problem referring to the technique of reconstructing a high-resolution (HR) image from a low-resolution (LR) image [1]–[3] to obtain more helpful”
MethodSobieranski, A. C., İnci, F., Tekin, H. C., Yüksekkaya, M. E., Comunello, E., Cobra, D. T., von Wangenheim, A., & Demirci, U. (2015) · Light Science & Applications · doi:10.1038/lsa.2015.119 · Cited by 136
A robust adaptive spatial and temporal image fusion model for complex land surface changes
Zhao, Y., Huang, B., & Song, H. (2018) · Remote Sensing of Environment · doi:10.1016/j.rse.2018.02.009 · Cited by 136
Ma, W., Pan, Z., Guo, J., & Lei, B. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2885506 · Cited by 135
“DL-based methods are also used to address the ill-posed inverse problem of SR due to their powerful learning ability, and have obviously boosted the performance of nonDL-based SR methods [19]–[23].”
MethodA Self-Learning Approach to Single Image Super-Resolution
Yang, M.-C., & Wang, Y.-C. F. (2012) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2012.2232646 · Cited by 125
“Since single-image SR does not require multiple LR images as inputs, it attracts the interest from researchers and engineers due to practical applications.”
BackgroundMethodSuper-Resolution of Single Remote Sensing Image Based on Residual Dense Backprojection Networks
Pan, Z., Ma, W., Guo, J., & Lei, B. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2917427 · Cited by 131
“Nonlocal priors refer to that natural images usually contain much nonlocal redundancy, and the super-resolved patch can be estimated either by searching its similar patches in the input image pyramid [6], [7] or through constructing the regularized term [8], [9].”
BackgroundMutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Liang, J., Sun, G., Zhang, K., Gool, L. V., & Timofte, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00406 · Cited by 165
Context-constrained hallucination for image super-resolution
Sun, J. Z., Zhu, J., & Tappen, M. F. (2010) · 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.2010.5540206 · Cited by 123
“The method in [11] performs well through self-learning.”
BackgroundMethodInfluentialMulti-scale dictionary for single image super-resolution
Zhang, K., Gao, X., Tao, D., & Li, X. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247791 · Cited by 115
“In recent years, a large number of SR methods (e.g., [8] [14] [4]) that combine the reconstruction-and examplebased methods into a unified SR framework have been acknowledged as an efficient way to produce more compelling SR results.”
BackgroundMethodZhao, N., Wei, Q., Basarab, A., Dobigeon, N., Kouamé, D., & Tourneret, J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2567075 · Cited by 165
Balanced Two-Stage Residual Networks for Image Super-Resolution
Fan, Y., Shi, H., Yu, J., Liu, D., Han, W., Yu, H., Wang, Z., Wang, X., & Huang, T. S. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.154 · Cited by 131
“Given the origin of example pairs, these methods can be further categorized into three classes: self-example based [9, 7], external-example based methods [42, 34] and the joint of them [39].”
MethodGodard, C., Matzen, K., & Uyttendaele, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01267-0_33 · Cited by 141
Computing nearest-neighbor fields via Propagation-Assisted KD-Trees
He, K., & Sun, J. (2012) · 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.2012.6247665 · Cited by 140
“Non-parametric patch sampling is of central importance in various computer vision/graphics algorithms, including image inpainting/retargeting [31, 28], denoising [8, 10], texture synthesis [13, 30], super-resolution [17], matching self-similarities [26], and rendering [21].”
BackgroundNaive Bayes Super-Resolution Forest
Salvador, J., & Pérez-Pellitero, E. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.45 · Cited by 133
“One possible strategy is internal learning [10, 8, 29], where the cross-scale selfsimilarity property of small (square) natural image patches is exploited to regress the appearance of high-resolution patches.”
BackgroundSpace-time super-resolution from a single video
Shahar, O., Faktor, A., & Irani, M. (2011) · 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.2011.5995360 · Cited by 121
“[9] regarding natural images, we observe that ‘natural videos’ (a) KTH dataset (b) HOHA dataset Figure 3.”
BackgroundMethodInfluentialSelf-citationSingle Image Super-resolution Using Deformable Patches
Zhu, Y., Zhang, Y., & Yuille, A. (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.2014.373 · Cited by 125
“Another research direction [8, 11] utilizes the self-similarity based on the fact that local image structures tend to repeat within and across the scales.”
BackgroundInfluentialSingle Image Interpolation Via Adaptive Nonlocal Sparsity-Based Modeling
Romano, Y., Protter, M., & Elad, M. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2325774 · Cited by 121
“Two such powerful priors that have widespread use in recent years are (i) non-local proximity and (ii) SparseLand modeling.”
BackgroundNon-uniform Blind Deblurring by Reblurring
Bahat, Y., Efrat, N., & Irani, M. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.356 · Cited by 136
“The patch recurrence property is very strong in sharp natural images [5, 24].”
BackgroundSelf-citationNon-Local Kernel Regression for Image and Video Restoration
Zhang, H., Yang, J., Zhang, Y., & Huang, T. S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15558-1_41 · Cited by 118
“[10] fully explores the self-similarity property for single image superresolution, but no spatial structural regularization is applied.”
BackgroundMethodResultInfluentialToward Long-Distance Subdiffraction Imaging Using Coherent Camera Arrays
Holloway, J., Asif, M. S., Sharma, M. K., Matsuda, N., Horstmeyer, R. W., Cossairt, O. S., & Veeraraghavan, A. (2016) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2016.2557067 · Cited by 117
“Exemplar based efforts to improve the super-resolution factor beyond 2 use large dictionaries to hallucinate information [31], [32] and offer no guarantees on fidelity.”
BackgroundEfficient Non-local Contrastive Attention for Image Super-resolution
Xia, B., Hang, Y., Tian, Y., Yang, W., Liao, Q., & Zhou, J. N. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20179 · Cited by 141
Underwater Image Super-Resolution using Deep Residual Multipliers
Islam, J., Enan, S. S., Luo, P., & Sattar, J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197213 · Cited by 129
“Some of the classical SISR methods include statistical methods [16], [17], [18], patch-based methods [19], [20], [21], sparse representation-based methods [22], random forestbased method [23], etc.”
MethodAdaptive Image Denoising by Targeted Databases
Luo, E., Chan, S. H., & Nguyen, T. Q. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2414873 · Cited by 133
Single-frame super-resolution in remote sensing: a practical overview
Fernández-Beltrán, R., Carmona, P., & Pla, F. (2016) · International Journal of Remote Sensing · doi:10.1080/01431161.2016.1264027 · Cited by 117
Multimedia super-resolution via deep learning: A survey
Hayat, K. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2018.07.005 · Cited by 123
“The successive refinements are based on searching non-local self-similarities in order to enhance the high-frequency details of the patches to which the image is partitioned in a way similar to the internal example-based method [37], as pointed out in [95].”
BackgroundMethodAwasthi, N., Jain, G., Kalva, S. K., Pramanik, M., & Yalavarthy, P. K. (2020) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2020.2977210 · Cited by 123
Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution
Liang, Z., Wang, Y., Wang, L., Yang, J., Zhou, S., & Guo, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01137 · Cited by 115
“Non-local means [5] is a classical algorithm that computes the weighted mean of pixels in an image according to the self-similarity measure, and a number of studies on such non-local priors have been proposed for image restoration [12, 51, 19, 4], image and video SR [16, 76, 14, 71, 23].”
BackgroundNLH: A Blind Pixel-Level Non-Local Method for Real-World Image Denoising
Hou, Y., Xu, J., Liu, M., Liu, G., Liu, L., Zhu, F., & Shao, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2980116 · Cited by 118
“Non-local Self Similarity (NSS): The NSS image prior is the essence to the success in texture synthesis [51], image denoising [3], super-resolution [52], inpainting [53], and video classification [54].”
BackgroundReview of image interpolation and super-resolution
Siu, W.-C., & Hung, K.-W. (2012) · PolyU Institutional Research Archive (Hong Kong Polytechnic University) · Cited by 108
Fast Image Interpolation via Random Forests
Huang, J., Siu, W.-C., & Liu, T. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2440751 · Cited by 110
“Image interpolation is a special type of image super-resolution [1-11], where the LR image is directly down-sampled from the HR image without an anti-aliasing”
BackgroundProgressive Sparse Local Attention for Video Object Detection
Guo, C., Fan, B., Gu, J., Zhang, Q., Xiang, S., Prinet, V., & Pan, C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00401 · Cited by 126
“n temporal spatial domain towards aligning two feature maps. Nonlocal and Local Operators. Nonlocal is a traditional filter algorithm [2] that is widely used in image denoise [3, 23], super-resolution [14] and texture synthesis [10]. Those approaches compute response as a weighted mean of all the pixeles in an image, w…”
MethodHierarchical Super-Resolution-Based Inpainting
Meur, O. L., Ebdelli, M., & Guillemot, C. M. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2261308 · Cited by 113
Image Super Resolution Based on Fusing Multiple Convolution Neural Networks
Ren, H., El‐Khamy, M., & Lee, J. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.142 · Cited by 113
Joint Super Resolution and Denoising From a Single Depth Image
Xie, J., Feris, R., Yu, S.-S., & Sun, M. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2457678 · Cited by 104
Conditioned Regression Models for Non-blind Single Image Super-Resolution
Riegler, G., Schulter, S., Rüther, M., & Bischof, H. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.67 · Cited by 119
“[11] who exploit the assumption that small patches often re-occur within the same image and across different scales.”
BackgroundMethodInfluentialImage Super-Resolution Based on Structure-Modulated Sparse Representation
Zhang, Y., Liu, J., Yang, W., & Guo, Z. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2431435 · Cited by 108
“Correspondingly, single-image super-resolution methods can also be further divided into interpolation-based methods [27], [28], reconstruction-based methods [13] and example learning-based methods [9], [10], [29].”
BackgroundMethodInfluentialSingle-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples
Bevilacqua, M., Roumy, A., Guillemot, C. M., & Morel, M.-L. A. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2364116 · Cited by 103
“In this respect, there are two main kinds of learning schemes described in the literature: one-step schemes like in [18], [21], and [22], and schemes involving the construction of a pyramid of recursively scaled images [23]–[25].”
BackgroundMethodInfluentialCascaded Deep Networks With Multiple Receptive Fields for Infrared Image Super-Resolution
He, Z., Tang, S., Yang, J., Cao, Y., Yang, M. Y., & Cao, Y. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2864777 · Cited by 110
“Several methods [9], [24] exploited the self-similarity prior that patches in a natural image tend to recur within and across scales of the same image.”
MethodSingle Infrared Image Stripe Noise Removal Using Deep Convolutional Networks
Kuang, X., Sui, X., Chen, Q., & Gu, G. (2017) · IEEE photonics journal · doi:10.1109/jphot.2017.2717948 · Cited by 103
“In addition, when we try a deeper network (5 layers), we find that it is difficult to initialize the appropriate parameters to ensure convergence as shown in [30].”
BackgroundDepth Super Resolution by Rigid Body Self-Similarity in 3D
Hornáček, M., Rhemann, C., Gelautz, M., & Rother, C. (2013) · 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.2013.149 · Cited by 99
“[8]— and the code used in carrying out the quantitative evaluation are from Mac Aodha et al.”
MethodInfluentialSeparating Signal from Noise Using Patch Recurrence across Scales
Zontak, M., Mosseri, I., & Irani, M. (2013) · 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.2013.158 · Cited by 108
“It was previously shown [7, 16] that small patches in clean natural images tend to recur across image scales.”
BackgroundMethodSelf-citationJoint Example-Based Depth Map Super-Resolution
Li, Y., Xue, T., Sun, L., & Liu, J. (2012) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2012.30 · Cited by 98
“Yang et al. proposed an example-based 2D image SR approach using sparse signal representation [11].”
MethodEnhancing images of shale formations by a hybrid stochastic and deep learning algorithm
Kamrava, S., Tahmasebi, P., & Sahimi, M. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.07.009 · Cited by 106
Maintaining Natural Image Statistics with the Contextual Loss
Mechrez, R., Talmi, I., Shama, F., & Zelnik‐Manor, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_27 · Cited by 120
“nt approach is to prefer image-specic priors, learned only from the image to be restored, without any external information from other images. This has been shown eective for a range of applications [17,18,19,20]. Recently, attempts have been made to utilize image-specic priors within the CNN framework, by training a n…”
BackgroundDeep Residual Squeeze and Excitation Network for Remote Sensing Image Super-Resolution
Gu, J., Sun, X., Zhang, Y., Fu, K., & Wang, L. (2019) · Remote Sensing · doi:10.3390/rs11151817 · Cited by 102
“Haut et al. [18] learn the distribution of the image based on GAN and proposed an unsupervised SISR method.”
BackgroundA Unified Learning Framework for Single Image Super-Resolution
Yu, J., Gao, X., Tao, D., Li, X., & Zhang, K. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2281313 · Cited by 96
Guo, Z., Zheng, H., Jiang, Y., Gu, Z., & Zheng, B. (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/cvpr46437.2021.01610 · Cited by 130
“…material ( e.g ., the top example in Figure 1), and a single natural image has powerful internal statistics that small patches recur abundantly [18, 61, 22], so compositing an image realistically and meaningfully should also follow this statistics, hence, we devise an inharmony-free learning…”
MethodSingle Image Super-resolution With Detail Enhancement Based on Local Fractal Analysis of Gradient
Xu, H., Zhai, G., & Yang, X. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2013.2248305 · Cited by 97
“On the other hand, compared with the example-based method in [9], [11], and [12], our method does not involve complex search step over a large data set, and therefore has relatively lower computational complexity.”
BackgroundMethodResultInfluentialVideo Superresolution via Motion Compensation and Deep Residual Learning
Li, D., & Wang, Z. (2017) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2017.2671360 · Cited by 101
“Internal base SR methods [39]–[43] use the self-similarities of the patches in the input image and perform well when there are sufficient recurrent textures.”
MethodSingle Image Blind Deblurring Using Multi-Scale Latent Structure Prior
Bai, Y., Jia, H., Jiang, M., Liu, X., Xie, X., & Gao, W. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2919159 · Cited by 105
NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results
Cai, J., Gu, S., Timofte, R., Zhang, L., Liu, X., Ding, Y., He, D., Li, C., Fu, Y., Wen, S., et al. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00274 · Cited by 122
“…of plausible corresponding HR images is huge and scales up quadratically with the magnification factor, learning image prior information from the HR and/or LR exem-plar images [13, 10, 42, 15, 11, 3, 20, 43, 8, 16, 35, 31] plays an indispensable role in recovering the details from an LR input image.”
BackgroundImage super-resolution via channel attention and spatial graph convolutional network
Yang, Y., & Qi, Y. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107798 · Cited by 101
PlenoPatch: Patch-Based Plenoptic Image Manipulation
Zhang, F., Wang, J., Shechtman, E., Zhou, Z., Shi, J., & Hu, S. (2016) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2016.2532329 · Cited by 94
“These include image-based rendering [12], hole-filling [53], texture synthesis [10], retargeting and reshuffling [9], super-resolution [15], morphing [43], image compositing and interpolation [8] and HDR reconstruction [41].”
Blind dehazing using internal patch recurrence
Bahat, Y., & Irani, M. (2016) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2016.7492870 · Cited by 99
“This patch recurrence property has been used as a strong prior to solve a variety of ill-posed vision problems, including super-resolution [6], image denoising [1,2], image completion [3], and more.”
MethodSelf-citationMulti-scale Weighted Nuclear Norm Image Restoration
Yair, N., & Michaeli, T. (2018) · 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.2018.00334 · Cited by 108
“Cross-scale patch recurrence Small patterns recur not only within the same scale, but also across different scales of the image [22, 50].”
BackgroundMethodInfluentialUncertainty in Machine Learning Applications: A Practice-Driven Classification of Uncertainty
Kläs, M., & Vollmer, A. M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99229-7_36 · Cited by 96
Single image super-resolution based on a modified U-net with mixed gradient loss
Lu, Z., & Chen, Y. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-02063-5 · Cited by 115
“The goal of super-resolution methods is to recover a high-resolution image from a low-resolution image [20].”
Background
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.