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 501–600 of 1,002
A Shrinkage Learning Approach for Single Image Super-Resolution with Overcomplete Representations
Adler, A., Hel-Or, Y., & Elad, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_45 · Cited by 28
“A combination of the example-based approach with multi-frame super-resolution was proposed in [5], where patch repetitions within an image were exploited in a multi-scale approach.”
MethodResultParameswaran, S., Deledalle, C., Denis, L., & Nguyen, T. Q. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2866691 · Cited by 33
A Deep Learning Framework for Joint Image Restoration and Recognition
Chen, R., Mihaylova, L. S., Zhu, H., & Bouaynaya, N. C. (2019) · Circuits Systems and Signal Processing · doi:10.1007/s00034-019-01222-x · Cited by 28
“The algorithms reported in [10,14,27,30] achieve state-of-the-art performance on a single image with super-resolution [9].”
BackgroundSpatial Transformer Generative Adversarial Network for Robust Image Super-Resolution
Kasem, H. M., Hung, K.-W., & Jiang, J. (2019) · IEEE Access · doi:10.1109/access.2019.2959940 · Cited by 28
“patch-based methods [15], [16] and sparse representation methods [13], [17], etc.”
MethodCoupled K-SVD dictionary training for super-resolution
Xu, J., Qi, C., & Chang, Z. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025794 · Cited by 27
“Glasner’s method [26] provides sharp edges, but introduces noticeable visual artifacts (e.”
MethodSingle face image super-resolution via solo dictionary learning
Juefei-Xu, F., & Savvides, M. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351199 · Cited by 27
“Through searching similar patches within the image itself across different scales, the algorithm gives rise to the super-resolution such as in [1, 2].”
BackgroundA New 4-D Nonlocal Transform-Domain Filter for 3-D Magnetic Resonance Images Denoising
Kong, Z., Han, L., Liu, X., & Yang, X. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2778230 · Cited by 28
Generative Adversarial Image Super‐Resolution Through Deep Dense Skip Connections
Zhu, X., Li, Z., Zhang, X., Li, H., Xue, Z., & Wang, L. (2018) · Computer Graphics Forum · doi:10.1111/cgf.13568 · Cited by 27
“The internal example-based method exploited the self-similarity property and generate exem-plar patches from the input image [FF11,GBI09].”
MethodSparsity inspired pan-sharpening technique using multi-scale learned dictionary
Gogineni, R., & Chaturvedi, A. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.10.009 · Cited by 27
A Total Fractional-Order Variation Model for Image Super-Resolution and Its SAV Algorithm
Yao, W., Shen, J., Guo, Z., Sun, J., & Wu, B. (2020) · Journal of Scientific Computing · doi:10.1007/s10915-020-01185-1 · Cited by 29
PatchNR: learning from very few images by patch normalizing flow regularization
Altekrüger, F., Denker, A., Hagemann, P., Hertrich, J., Maaß, P., & Steidl, G. (2023) · Inverse Problems · doi:10.1088/1361-6420/acce5e · Cited by 35
“To this end, we combine some concepts of zero-shot superresolution by internal learning [25, 73] with patchNRs.”
BackgroundMethodHyperspectral Image Compression via Cross-Channel Contrastive Learning
Guo, Y., Chong, Y., & Pan, S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3282186 · Cited by 29
“Once the positive channel is defined, the remaining channels of Y X are regarded as negative samples due to the internal image statistics [37], [39].”
BackgroundLightweight image super-resolution based multi-order gated aggregation network
Gendy, G., Sabor, N., & He, G. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.07.002 · Cited by 27
Robust Super-Resolution for Mixed-Resolution Multiview Image Plus Depth Data
Richter, T., Seiler, J., Schnurrer, W., & Kaup, A. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2426498 · Cited by 27
“For this, it is assumed that patches in a natural image redundantly occur many times, both in one resolution level and across different resolution levels [11], [12].”
BackgroundMulti-Scale Inception Based Super-Resolution Using Deep Learning Approach
Muhammad, W., & Aramvith, S. (2019) · Electronics · doi:10.3390/electronics8080892 · Cited by 28
“Super-resolution (SR) is an image, video, and computer vision task that reconstruct the high quality or high-resolution (HR) image with large texture detail information from a single or multiple low quality or low-resolution (LR) image [1,2], under the limited conditional environment and low-cost imaging system.”
BackgroundSingle Image Super-Resolution using Residual Channel Attention Network
Basak, H., Kundu, R., Agarwal, A., & Giri, S. (2020) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciis51140.2020.9342688 · Cited by 32
“A framework combining both the reconstruction and learning-based SR was introduced by Glasner et al. [25].”
MethodLearning to Maintain Natural Image StatisticsPreprint
Mechrez, R., Talmi, I., Shama, F., & Zelnik‐Manor, L. (2018) · arXiv (Cornell University) · Cited by 28
Robust Image Restoration via Adaptive Low-Rank Approximation and Joint Kernel Regression
Huang, C., Ding, X., Fang, C., & Wen, D. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2363734 · Cited by 29
“[20], Freedman and Fattal [23], Yang et al.”
BackgroundEfficient sparse representation based image super resolution via dual dictionary learning
Zhang, H., Zhang, Y., & Huang, T. S. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6011877 · Cited by 26
“Furthermore, SR methods exploit ing self-similarities [4] and exploiting both local structural regularities as well as the image self-similarities [5] are two recent promising directions.”
BackgroundMethodFast single image super-resolution using sparse Gaussian process regression
Wang, H., Gao, X., Zhang, K., & Li, J. (2016) · Signal Processing · doi:10.1016/j.sigpro.2016.11.006 · Cited by 26
Learning local dictionaries and similarity structures for single image super-resolution
Zhang, K., Li, J., Wang, H., Liu, X., & Gao, X. (2017) · Signal Processing · doi:10.1016/j.sigpro.2017.07.020 · Cited by 26
RAW Image Reconstruction Using a Self-contained sRGB–JPEG Image with Small Memory Overhead
Nguyen, R. M. H., & Brown, M. S. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1056-0 · Cited by 26
“Representative work includes interpolation-based methods (Hou and Andrews 1978; Thévenaz et al. 2000), edge-based methods (Dai et al. 2007; Fattal 2007; Sun et al. 2008), and example-based meth-ods (Freeman et al. 2000; Glasner et al. 2009).”
MethodImage super‐resolution via adaptive sparse representation and self‐learning
Zhao, J., Sun, T., & Cao, F. (2018) · IET Computer Vision · doi:10.1049/iet-cvi.2017.0153 · Cited by 26
Chien, J. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-804566-4.00019-x · Cited by 32
Hierarchical residual learning for image denoising
Shi, W., Jiang, F., Zhang, S., Wang, R., Zhao, D., & Zhou, H. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.05.007 · Cited by 30
“Make full use multiple scales information can improve the restoration result has been proved in traditional method [23].”
MethodSuper-resolution of spatiotemporal event-stream image
Li, H., Li, G., & Shi, L. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.12.048 · Cited by 30
Receptive Field Size Versus Model Depth for Single Image Super-Resolution
Wang, R., Gong, M., & Tao, D. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2941327 · Cited by 27
Single image super-resolution approaches in medical images based-deep learning: a survey
El‐Shafai, W., Ali, A. M., El‐Nabi, S. A., El‐Rabaie, E. M., & El‐Samie, F. E. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16197-w · Cited by 29
“It was also noted in [45] that natural digital images are repetitive.”
Single Image Super Resolution in Spatial and Wavelet Domain
Naik, S., & Patel, N. (2013) · The International journal of Multimedia & Its Applications · doi:10.5121/ijma.2013.5402 · Cited by 26
“Some of the most recent work on single image super resolution has been done using texture hallucination, patch based up sampling and example based super resolution [3,14].”
BackgroundImage Super-Resolution Via Analysis Sparse Prior
Ning, Q., Chen, K., Li, Y. C., Fan, C., Lu, Y., & Wen, J. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2242198 · Cited by 26
“Algorithms for image SR can be categorized into following families: Interpolation based [1], Reconstruction based [2], [3], Self-based [4], [5] and Learning based methods [6]–[8].”
MethodInfluentialIterative projection reconstruction for fast and efficient image upsampling
Zhao, Y., Wang, R., Jia, W., Wang, W., & Gao, W. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.11.049 · Cited by 26
Patch-Based Desynchronization of Digital Camera Sensor Fingerprints
Entrieri, J., & Kirchner, M. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.8.mwsf-087 · Cited by 28
“This self-similarity has been exploited in various forms, for instance for image coding [24], texture synthesis [25], denoising [26], or super-resolution [23].”
BackgroundMethodMSCE: An Edge-Preserving Robust Loss Function for Improving Super-Resolution Algorithms
Pandey, R. K., Saha, N., Karmakar, S., & Ramakrishnan, A. G. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04224-0_49 · Cited by 31
Robust Single-Image Super-Resolution via CNNs and TV-TV Minimization
Vella, M., & Mota, J. F. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3108907 · Cited by 27
“A more challenging assumption is multi-scale recurrence [27], [28], which captures the notion that patches of natural images occur repeatedly across the image.”
BackgroundBinary Document Image Super Resolution for Improved Readability and OCR PerformancePreprint
Pandey, R. K., Vignesh, K., Ramakrishnan, A. G., & Chandrahasa, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.02475 · Cited by 35
“Generic SISR algorithms have priors based on common and primitive image properties [13] and can be applied to different kinds of images [8][14] [15].”
BackgroundMethodA Review of Satellite-Based CO2 Data Reconstruction Studies: Methodologies, Challenges, and Advances
Hu, K., Liu, Z., Shao, P., Ma, K., Yao, X., Wang, S., Wang, Y., Wang, H., Di, L., Xia, M., et al. (2024) · Remote Sensing · doi:10.3390/rs16203818 · Cited by 30
Underwater image restoration algorithm for free-ascending deep-sea tripods
Li, J., & Li, Y. (2018) · Optics & Laser Technology · doi:10.1016/j.optlastec.2018.05.034 · Cited by 27
(SARN)spatial-wise attention residual network for image super-resolution
Shi, W., Du, H., Mei, W., & Ma, Z. (2020) · The Visual Computer · doi:10.1007/s00371-020-01903-8 · Cited by 25
“The recurrence of small pieces of information (e.g., small image patches) of a single image, was shown to be a very strong property of natural images [17,18].”
BackgroundZhang, N., Wang, Y., Zhang, X., Xu, D., Wang, X., Ben, G., Zhao, Z., & Li, Z. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3042460 · Cited by 28
“There are several classical unsupervised SR methods before the rise of DL such as the example-based method [20]–[22] and blind SR method [40].”
BackgroundMethodInfluentialHuang, W., Xiao, L., Liu, H., & Wei, Z. (2015) · Sensors · doi:10.3390/s150102041 · Cited by 25
“Generally, these methods can be categorized into three classes: interpolation-based methods [3,4], multi-image-based methods [2,5,6], and example-based learning methods for single image SR [7–9].”
MethodScholkmann, F., Revol, V., Kaufmann, R., Baronowski, H., & Kottler, C. (2014) · Physics in Medicine and Biology · doi:10.1088/0031-9155/59/6/1425 · Cited by 26
Image de-fencing framework with hybrid inpainting algorithm
Farid, M. S., Mahmood, A., & Grangetto, M. (2016) · Signal Image and Video Processing · doi:10.1007/s11760-016-0876-7 · Cited by 25
“, [12,13,28,33], can be used to upsample the inpainted image; however, such methods usually take considerable amount of execution time.”
BackgroundFractal Dimension Invariant Filtering and Its CNN-Based Implementation
Xu, H., Yan, J., Persson, N. E., Lin, W., & Zha, H. (2017) · 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.2017.407 · Cited by 26
“Because the local self-similarity of image is often ubiquitous both within and across scales [15, 12], natural images can also be modeled as fractals locally [21, 29].”
BackgroundSK-SVR: Sigmoid kernel support vector regression based in-scale single image super-resolution
Jebadurai, J., & Peter, J. D. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.04.013 · Cited by 25
Deep recursive up-down sampling networks for single image super-resolution
Li, Z., Li, Q., Wu, W., Yang, J., Li, Z., & Yang, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.004 · Cited by 25
Finding Discriminative Filters for Specific Degradations in Blind Super-ResolutionPreprint
Xie, L., Wang, X., Dong, C., Qi, Z., & Shan, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.01070 · Cited by 46
“This design incorporates human knowledge about the degradation process [8, 23] and is consistent in classical blind SR methods [28, 11], thus implying a certain degree of interpretability.”
BackgroundMethodSelf-learning approach to color demosaicking via support vector regression
He, F.-L., Wang, Y.-C. F., & Hua, K. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467472 · Cited by 24
“In this work, we downgrade the input image into different smaller scales as ground truth data, as [6, 7, 8] did, for self-leaning purposes.”
MethodNovel infrared and visible image fusion method based on independent component analysis
Yin, L., Wang, F., Luo, X., & Liu, F. (2014) · Frontiers of Computer Science · doi:10.1007/s11704-014-2328-2 · Cited by 26
“The small image patches in a natural image tend to recur redundantly inside the image as discussed in image processing [25].”
BackgroundTwo-frames image superresolution based on the aggregate divergence matrix
Peleshko, D., Рак, Т., Peleshko, M., Izonin, I., & Batyuk, D. (2016) · IEEE International Conference on Data Stream Mining & Processing (DSMP) · doi:10.1109/dsmp.2016.7583548 · Cited by 24
“The same applies to the problem of superresolution [11], [12], [13], [14], [15].”
BackgroundKrig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_2 · Cited by 32
Video Snapshots: Creating High-Quality Images from Video Clips
Sunkavalli, K., Joshi, N., Kang, S. B., Cohen, M. F., & Pfister, H. (2012) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2012.72 · Cited by 24
“The snapshots we produce have higher resolution, lower noise, and less blur than the original video frames.”
BackgroundSingle image super resolution using local smoothness and nonlocal self-similarity priors
Chen, H., He, X., Teng, Q., & Ren, C. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.01.007 · Cited by 24
Statistics of Natural Stochastic Textures and Their Application in Image Denoising
Zachevsky, I., & Zeevi, Y. Y. J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2539689 · Cited by 25
“Self-similarity also describes the accurate shape resemblance of a specific search pattern (or patch) in an image across scales [12].”
BackgroundMulti-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution
Lee, O.-Y., Shin, Y.-H., & Kim, J. (2019) · IEEE Access · doi:10.1109/access.2019.2942779 · Cited by 25
Self-Supervised Test-Time Learning for Reading Comprehension
Banerjee, P., Gokhale, T., & Baral, C. R. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.95 · Cited by 42
MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution
Xie, C., Zhang, X., Li, L., Fu, Y., Gong, B., Li, T., & Zhang, K. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3553135 · Cited by 35
“Two fundamental priors widely used for this purpose are image locality [1], [2] and redundancy [3], [4], [5].”
Single image super-resolution using self-examples and texture synthesis
Damkat, C. (2011) · Signal Image and Video Processing · doi:10.1007/s11760-010-0205-5 · Cited by 23
“Glasner et al. [ 9 ] recently proposed a method that performs single image super-resolution by a combination of classical super-resolution and example-based super-resolution.”
MethodMulti-frame example-based super-resolution using locally directional self-similarity
Jeong, S., Yoon, I., & Paik, J. (2015) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2015.7298295 · Cited by 23
Super-resolution of Magnetic Resonance Images using deep Convolutional Neural Networks
Srinivasan, K., Ankur, A., & Sharma, A. (2017) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-china.2017.7990985 · Cited by 23
A deep learning method for image super-resolution based on geometric similarity
Lü, J., Hu, W., & Sun, Y. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.10.003 · Cited by 25
Semantic-Driven Face Hallucination Based on Residual Network
Yu, X., Zhang, L., & Xie, W. C. (2021) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2021.3051268 · Cited by 23
“Prior-based methods [25]–[30] often design several priors and constraints to obtain the flexible and plea-suring result during the designed possible solution space.”
MethodDeep Random Projector: Accelerated Deep Image Prior
Li, T., Wang, H., Zhuang, Z., & Sun, J. (2023) · 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/cvpr52729.2023.01743 · Cited by 46
High Resolution Local Structure-Constrained Image Upsampling
Zhao, Y. S., Wang, R., Wang, W., & Gao, W. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2456416 · Cited by 24
“In [24], [25], and [45], local self-example-based methods were introduced by consideration of the similarities of local patches in different scales of the same image.”
MethodImage Upscaling Using Multiple Dictionaries of Natural Image Patches
Purkait, P., & Chanda, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37431-9_22 · Cited by 23
“[7] merge the concepts of both singleframe SR and multi-frame SR for HR image reconstruction from a single-frame.”
BackgroundMethodThe Topological Gradient Method: From Optimal Design to Image Processing
Larnier, S., Fehrenbach, J., & Masmoudi, M. (2012) · Milan Journal of Mathematics · doi:10.1007/s00032-012-0196-5 · Cited by 29
“The purpose of super-resolution techniques is to obtain a high resolution image from one or several low resolution images [52, 37].”
BackgroundTang, Z., Deng, M., Xiao, C., & Yu, J. S. (2011) · Electronic and Mechanical Engineering and Information Technology · doi:10.1109/emeit.2011.6022950 · Cited by 23
“Although the frequency domain methods are intuitively simple and computationally attractive, their sensitivity to model errors limits its usage [ 2 , 3]. Recently, the spatial domain methods have attracted increased attention and become the main choice for SR image reconstruction.”
BackgroundMethodLearning to Incorporate Structure Knowledge for Image InpaintingPreprint
Yang, J., Qi, Z., & Shi, Y. G. (2020) · Preprints.org · doi:10.20944/preprints202002.0125.v1 · Cited by 29
“dual block (He et al. 2016). Attention Layer Our attention operation is inspired by the non-local mean mechanism which has been used for deionizing (Buades, Coll, and Morel 2005) and superresolution (Irani 2009). It calculates the response at a position of the output feature map as a weighted sum of the features in th…”
MethodQin, M., Hu, L., Du, Z., Gao, Y. C., Qin, L., Zhang, F., & Liu, R. (2020) · Remote Sensing · doi:10.3390/rs12121937 · Cited by 22
“In the proposed method, unsupervised learning is based on the hypothesis that the repeated occurrence of small image patches across scales of a single image is a very strong property of natural images [33,34].”
MethodGuo, T., & Xu, X. (2020) · The Visual Computer · doi:10.1007/s00371-020-01964-9 · Cited by 23
“The non-local block has made great achievements in texture [45], super-resolution [46], and inpainting [47].”
BackgroundMethodBoosting Event Stream Super-Resolution with a Recurrent Neural Network
Weng, W., Zhang, Y., & Xiong, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20068-7_27 · Cited by 29
“Classic methods aim to super-resolve images by exploiting the statistical image priors to build a regression function from LR to HR images, which can be achieved by neighbor embedding [2, 7], sparse coding [49, 50, 65, 67] and internal patch recurrence [19, 24].”
MethodFigure Text Extraction in Biomedical Literature
Kim, D. H., & Yu, H. Q. (2011) · PLoS ONE · doi:10.1371/journal.pone.0015338 · Cited by 22
“We will also explore techniques implementing super-resolution [51,52] to improve image quality.”
MethodSuper-resolution using neighbor embedding of back-projection residuals
Bevilacqua, M., Roumy, A., Guillemot, C. M., & Morel, M.-L. A. (2013) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2013.6622796 · Cited by 22
“[11], which requires the SR procedure to be repeated several times for smaller scale factors.”
MethodInfluentialNeedle-Match: Reliable Patch Matching under High Uncertainty
Lotan, O., & Irani, M. (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.2016.54 · Cited by 22
“Replacing the patch-matching in [14] with NeedleMatch, results in a super-resolved image with reconstructed high-frequency signal details, while discarding the noise (please zoom in on Fig.”
InfluentialSelf-citationAnchored neighborhood regression based single image super-resolution from self-examples
Tian, Y., Zhou, F., Yang, W., Shang, X., & Liao, Q. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532875 · Cited by 22
“[2] presented a unified SR framework that combines classical multi-image and example-based SR methods.”
BackgroundMethodInfluentialIsophote-Constrained Autoregressive Model With Adaptive Window Extension for Image Interpolation
Yang, W., Liu, J., Li, M., & Guo, Z. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2638864 · Cited by 22
“These methods include MRF fusion [28], local selfexamples [29], edge statistics [30], support vector regression [31], kernel ridge regression [32], multiscale similarity [33], sparse representation [21], [34], simple function mapping [35], anchor neighbor regression [36], [37], and random forest [38], among others.”
MethodRotation and script independent text detection from video frames using sub pixel mapping
Mittal, A., Roy, P. P., Singh, P., & Raman, B. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.03.002 · Cited by 22
“There exist only a limited work [42] in the area of single frame non-training based super resolution.”
BackgroundSuper-Resolved Fine-Scale Sea Ice Motion Tracking
Xian, Y., Petrou, Z. I., Tian, Y., & Meier, W. N. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2699081 · Cited by 22
“Learning can be performed either via an external data set [26]–[29], within the input image [30]–[33], or combined [34].”
BackgroundMethodFPGA-Based Real-Time Super-Resolution System for Ultra High Definition Videos
He, Z., Huang, H., Jiang, M., Bai, Y., & Luo, G. (2018) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm.2018.00036 · Cited by 26
“These approaches either exploit internal similarity of the same image [6], [7], or learn the mapping function from external exemplar pairs [5], [11].”
BackgroundFeature Learning and Deep Learning Architecture Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_10 · Cited by 25
Chen, J., Xing, D., Shabaz, M., Zhu, Y., Wang, Y., & Zhu, X. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105721 · Cited by 21
Zou, Y., Chen, Z., Zhang, Z. Y., Li, X., Ma, L., Liu, J., Wang, P., & zhang, Y. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02668-0 · Cited by 40
“Image super-resolution (SR) (Glasner et al., 2009; Dong et al., 2015; Lim et al., 2017) aims to enhance an LR image to its HR counterpart, bypassing the need for hardware modifi-cations.”
Local Means Binary Networks for Image Super-Resolution
Li, K., Wang, N., Xin, J., Jiang, X., Li, J., Gao, X., Han, K., & Wang, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3212827 · Cited by 23
“A S A TYPICAL low-level computer vision task, single image super-resolution (SISR) has gained increasing attention in recent years [1], [2], [3], [4], [5], [6], [7], [8], [9], [10].”
BackgroundFast and High Quality Image Denoising via Malleable Convolution
Jiang, Y., Wronski, B., Mildenhall, B., Barron, J. T., Wang, Z., & Xue, T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19797-0_25 · Cited by 28
Li, L., Xie, Y., Hu, W., & Zhang, W. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.02.045 · Cited by 21
Super-resolution of single text image by sparse representation
Walha, R., Drira, F., Lebourgeois, F., & Alimi, A. M. (2012) · Workshop on Document Analysis and Recognition (DAR) · doi:10.1145/2432553.2432558 · Cited by 21
“Finally, similar to [14, 38], we apply on X0 a global reconstruction constraint to eliminate the reconstruction errors and to ensure consistency with the LR input image.”
MethodSingle-image superresolution based on local regression and nonlocal self-similarity
Hu, J., & Luo, Y. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.3.033014 · Cited by 21
“– 24,27,35 In particular, Glasner et al. 22 have unified the reconstruction-based SR and the self-learning SR in the same framework, where the same-scale patch recurrence forms the constraints used in reconstruction-based SR and the across-scale patch recurrence generates exemplar LR-HR patch pairs…”
BackgroundInfluentialAn incremental scheme for dictionary-based compressive SLAM
Tomomi, N., & Kanji, T. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094729 · Cited by 21
An iterative image super-resolution approach based on Bregman distance
Laghrib, A., Hakim, A., & Raghay, S. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.06.006 · Cited by 24
Baek, N. R., Cho, S. W., Koo, J. H., Truong, N. Q., & Park, K. R. (2019) · IEEE Access · doi:10.1109/access.2019.2932146 · Cited by 21
BP-DIP: A Backprojection based Deep Image Prior
Zukerman, J., Tirer, T., & Giryes, R. (2020) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco47968.2020.9287540 · Cited by 21
“Many image priors (of both kinds) also exploit the non-local similarity of natural images [4], [5].”
BackgroundParadigm shifts in super-resolution techniques for remote sensing applications
Rohith, G., & Kumar, L. S. (2020) · The Visual Computer · doi:10.1007/s00371-020-01957-8 · Cited by 24
Shen, B., Wang, R., Law, A. C. C., Kamath, R. R., Choo, H., & Kong, Z. (2021) · Technometrics · doi:10.1080/00401706.2021.1905074 · Cited by 23
“Practically, the multi-images super resolution has small improvement in resolution (Glasner, Bagon, and Irani 2009), leading to the development of single image super resolution in which the objective is to find an accurate mapping between low and high spatial resolution image pairs.”
BackgroundOmnidirectional Image Super-Resolution via Latitude Adaptive Network
Deng, X., Wang, H., Xu, M., Li, L., & Wang, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3171401 · Cited by 26
“Traditional image super-resolution (SR) tasks focus on the 2D planar images, which attempt to recover the original high-resolution image from a distorted LR image [3].”
BackgroundA Deep Pyramid Attention Network for Single Image Super-resolution
Gendy, G., Mohammed, H., Sabor, N., & He, G. (2021) · International Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC) · doi:10.1109/jac-ecc54461.2021.9691443 · Cited by 20
A Closed-Loop Network for Single Infrared Remote Sensing Image Super-Resolution in Real World
Zhang, H., Zhang, C., Xie, F., & Jiang, Z. (2023) · Remote Sensing · doi:10.3390/rs15040882 · Cited by 20
Efficient Super-Resolution System With Block-Wise Hybridization and Quantized Winograd on FPGA
Shi, B., Zhang, J., He, Z., Wei, X., Li, S., Luo, G., Zheng, H., & Xie, Y. (2023) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2023.3247621 · Cited by 20
“Previous works using interpolations [11], model-based methods [12], [13], and example-based methods [14], [15], [16] will be elaborated in Section II-A.”
BackgroundMethodUnfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution
Liu, Y., Dong, H., Liang, B., Liu, S., Dong, Q., Chen, K., Chen, F., Fu, L., & Wang, F. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612128 · Cited by 26
“Single Image Super-Resolution (SISR) [10] aims to reconstruct a high-resolution (HR) image from its low-resolution (LR) observation, which has received increasing research attention in multi-media and computer vision communities for decades.”
BackgroundChen, X., Chen, L., Chen, L., Chen, P., Sheng, G., Yu, X., & Zou, Y. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3349182 · Cited by 26
“Single image super-resolution [1] is a classical computer vision problem that aims to recover from a given low resolution (LR) image to a high resolution (HR) image.”
BackgroundRevealing the Dark Side of Non-Local Attention in Single Image Super-Resolution
Su, J.-N., Fan, G., Gan, M., Chen, G., Guo, W., & Chen, C. L. P. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3457790 · Cited by 21
Sub-band Energy Constraints for Self-Similarity Based Super-resolution
Singh, A., & Ahuja, N. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.761 · Cited by 20
“[6] and Freedman et. al [4], taken from the respective authors’ websites.”
BackgroundMethodInfluential
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.