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 901–1,000 of 1,002
Single image super-resolution via multiple linear mapping anchored neighborhood regression
Hardiansyah, B., & Lu, Y. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11062-0 · Cited by 9
“Different from aforementioned methods that rely on an external training dataset, recently state-of-art approaches to SR have been developed that exploit the self-similarity of structures in the LR input [13, 42, 43].”
MethodConvolutional Block Design for Learned Fractional Downsampling
Chen, L., Bampis, C. G., Li, Z., Chen, C., & Bovik, A. C. (2022) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf56349.2022.10052104 · Cited by 15
Adapting total generalized variation for blind image restoration
Shao, W., Wang, F., & Huang, L. (2018) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-018-0586-0 · Cited by 9
“…problem inherently in SISR is that most state-of-the-art methods (Dong et al. 2014; Kim et al. 2015; Yang et al. 2010, 2012, 2013, 2014; Glasner et al. 2009; Zeyde et al. 2012; Timofte et al. 2013; Peleg and Elad 2014; Timofte et al. 2014; Chang et al. 2004; Fattal 2007) including the…”
BackgroundFPA-CS: Focal Plane Array-based Compressive Imaging in Short-wave InfraredPreprint
Chen, H., Asif, M. S., Sankaranarayanan, A. C., & Veeraraghavan, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.04085 · Cited by 13
“However, traditional SR cannot arbitrarily increase resolution, and even state-of-the-art SR algorithms are limited to 2–4× upsampling [10].”
BackgroundNavigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution
Wang, H., Chen, J., Zheng, Y., & Zeng, T. (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/cvpr52733.2024.02412 · Cited by 11
“…of deep learning technology, Single Image Super-Resolution (SISR) with deep neural networks (DNNs) has greatly evolved in recent years (e.g., VDSR [35], SRResNet [38], EDSR [45], RDN [83] and SwinIR [43]), offering superior performances over traditional prediction models [21, 24, 31, 58].”
BackgroundBai, Y., Zhu, L., Sun, Y., Dong, M., & Yu, M. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.112814 · Cited by 8
Accelerating image super-resolution regression by a hybrid implementation in mobile devices
Amanatiadis, A. A., Bampis, L., & Gasteratos, A. C. (2014) · International Conference on Consumer Electronics · doi:10.1109/icce.2014.6776029 · Cited by 8
“Machine learning super-resolution, also known as example based super resolution, has been also introduced to numerous recent algorithms with very promising results [5], [6], yet, their main trade-off hides in their demanding learning phase making them inappropriate for real-time applications.”
BackgroundSingle image super-resolution via internal gradient similarity
Xian, Y., & Tian, Y. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.11.015 · Cited by 9
“Compared with edge-directed approaches, methods adopt internal image similarity [11,14] hallucinate more natural textures.”
BackgroundMethodResultInfluentialImproved interpolation kernels for super resolution algorithms
Rasti, P., Orlova, O., Tamberg, G., Ozcinar, C., Nasrollahi, K., Moeslund, T. B., & Anbarjafari, G. (2016) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2016.7820980 · Cited by 8
“But these algorithms usually differ from each other in the way they fine tune this initial HR image and/or converge to the desired HR image [26]–[28].”
BackgroundTopology and channel affinity reinforced global attention for person re‐identification
Wang, X., Gao, C., Xin, M., Zhang, S., & Zhang, M. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22506 · Cited by 8
“…mechanism can attend to the most informative components of input signals, which has been proved effective in various tasks, including texture synthesis, 39 super ‐ resolution, 40 inpainting, 41 and even high ‐ level tasks, such as image recognition, object segmentation, 12 and action localization.”
BackgroundDeep locally linear embedding network
Wang, J., Shao, Z., Huang, X., Lü, T., Zhang, R., & Chen, X. (2022) · Information Sciences · doi:10.1016/j.ins.2022.10.036 · Cited by 8
A new approach for super-resolution and classification applications on neonatal thermal images
ŞENALP, F. M., & Ceylan, M. (2023) · Quantitative InfraRed Thermography Journal · doi:10.1080/17686733.2023.2179282 · Cited by 9
Kernel Estimation Using Total Variation Guided GAN for Image Super-Resolution
Park, J., Kim, H., & Kang, M. G. (2023) · Sensors · doi:10.3390/s23073734 · Cited by 8
Image super-resolution reconstruction based on deep dictionary learning and A+
Huang, Y., Bian, W., Jie, B., Zhu, Z., & Li, W. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-023-02936-x · Cited by 8
“The LR input image itself can be used to build a dictionary, in which case there will be an "inner"dictionary[32].”
LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors
Suri, S., Walmer, M., Gupta, K., & Shrivastava, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72667-5_7 · Cited by 30
Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
Shang, W., Ren, D., Zhang, W., Fang, Y., Zuo, W., & Ma, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72998-0_5 · Cited by 21
Super-resolution of facial images in forensics scenarios
Satiro, J., Nasrollahi, K., Correia, P. L., & Moeslund, T. B. (2015) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2015.7367096 · Cited by 8
Limitations of Super Resolution Image Reconstruction and How to Overcome them for a Single Image
Gohshi, S., & Echizen, I. (2013) · International Conference on Signal Processing and Multimedia Applications · doi:10.5220/0004518300710078 · Cited by 8
“Although some technologies can improve resolution with a single image (Glasner et al., 2009)(Panda et al., 2011), they need iterations and the processing time depends on the characteristics of the image.”
BackgroundYang, G., Ye, X., Slabaugh, G., Keegan, J., Mohiaddin, R. H., & Firmin, D. N. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2207440 · Cited by 8
Texture enhancement for improving single-image super-resolution performance
Yoo, S. B., Choi, K., Jeon, Y. W., & Ra, J. B. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.04.007 · Cited by 8
“were proposed by exploiting the patch redundancy among in-scale and cross-scale images [13-15].”
BackgroundMethodInfluentialHalf hypersphere confinement for piecewise linear regression
Pérez-Pellitero, E., Salvador, J., Ruiz‐Hidalgo, J., & Rosenhahn, B. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477651 · Cited by 8
“[9] recently refined to extend the search domain via transformed patches [11], gradient priors such as [19] or those using deep learning [6, 3]).”
BackgroundLatent topic-based super-resolution for remote sensing
Fernández-Beltrán, R., Carmona, P., & Pla, F. (2017) · Remote Sensing Letters · doi:10.1080/2150704x.2017.1287974 · Cited by 8
Anchored fusion for image restoration
Timofte, R. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899835 · Cited by 8
“[12] use image self-similarity / patch redundancy and”
MethodRobust single image super resolution using neighbor embedding and fusion in wavelet domain
Rahiman, V. A., & George, S. N. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2017.09.020 · Cited by 9
Very low resolution face recognition using fused visual and texture features
Arya, K. V., Rajawat, A., Pandey, M. K., & Rajput, S. S. (2017) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/infocomtech.2017.8340642 · Cited by 9
“For this purpose number of works have been published [7], [8], [9], [6], [10], [11] Baker and Kanade [6] in 2000 proposed a method for the enhancement of the resolution of LR images with the assist of nearest neighbor algorithm by learning the priors at the spatial distribution of the image gradient for frontal images…”
MethodHow Does the Low-Rank Matrix Decomposition Help Internal and External Learnings for Super-Resolution
Wang, S., Yue, B., Liang, X., & Jiao, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2768185 · Cited by 9
High-quality as-is 3D thermal modeling in MEP systems using a deep convolutional network
Son, H., Kim, C., & Choi, H. (2019) · Advanced Engineering Informatics · doi:10.1016/j.aei.2019.100999 · Cited by 8
Yang, L., Sheng, Y., & Chai, L. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865120 · Cited by 8
“The nine SISR algorithms are Bicubic, Bp, Shan08, Glasner09 [13], Yang10 [14], Dong11 [15], Yang13 [16], Timofte13 [17], SRCNN [18].”
Image Super-Resolution Based on CNN Using Multilabel Gene Expression Programming
Tang, J., Huang, C., Liu, J., & Zhu, H. (2020) · Applied Sciences · doi:10.3390/app10030854 · Cited by 8
“Introduction Aiming at addressing image degradation during digital image acquisition and processing, Single-Image Super-Resolution (SISR) technology [1,2] enables high-resolution (HR) images to be recovered from low-resolution (LR) ones with high-frequency texture details and edge structure information observations of…”
BackgroundE-ProSRNet: An enhanced progressive single image super-resolution approach
Chudasama, V. M., & Upla, K. P. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.103038 · Cited by 8
A nonlocal Weickert type PDE applied to multi-frame super-resolution
Bella, F. Z. A., Hadri, A., Hakim, A., & Laghrib, A. (2020) · Evolution equations and control theory · doi:10.3934/eect.2020084 · Cited by 8
“Concerning the single frame SR technique, the missing high frequency information in the LR image during the acquisition step is estimated through a considerable number of training set images which complete the resolution of the LR image [15, 18, 39].”
MethodSingle Image Super-resolution Reconstruction with Wavelet based Deep Residual Learning
Dou, J., Tu, Z., & Peng, X. (2020) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc49329.2020.9164678 · Cited by 8
“Neural Networks (CNN), are widely used to address the ill-posed inverse problem of Super Resolution (SR), and have demonstrated superiority over reconstruction-based methods [12, 13] or other learning paradigms [14,15].”
BackgroundNon-local Second-Order Attention Network for Single Image Super Resolution
Lyn, J., & Yan, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-57321-8_15 · Cited by 8
“In order to obtain a super-resolution image, [11] use the patch redundancy to produce.”
Ground Truth Data, Content, Metrics, and Analysis
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_7 · Cited by 12
Gedkhaw, E., & Ketcham, M. (2022) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v18i02.28147 · Cited by 8
Benchmark of deep learning models for single image super-resolution (SISR)
Soufi, O., Aarab, Z., & Belouadha, F.-Z. (2022) · International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset52964.2022.9738274 · Cited by 9
Single-image reconstruction using novel super-resolution technique for large-scaled images
Datta, R., Mandal, S., Umer, S., AlZubi, A. A., Alharbi, A., & Alanazi, J. M. (2022) · Soft Computing · doi:10.1007/s00500-022-07142-4 · Cited by 9
“Then, it employs a large database of LR and HR patch pairs and uses a learning mechanism for the corresponding mapping between the LR and HR image patches that are applied to a new LR image to reconstruct its most likely HR version (Yang et al. 2010; Glasner et al. 2009).”
MethodWu, H., Gao, T. Y., Ji, Z., Song, M., Zhang, L., & Kong, D. (2023) · Sensors · doi:10.3390/s23218932 · Cited by 8
“To maintain the key object detail information of the road inspection image, one can consider using super-resolution networks to enhance the object feature [34–38], while the existing super-resolution networks are whole-image-oriented rather than object-oriented.”
Context-aware single image super-resolution using sparse representation and cross-scale similarity
Lü, J., & Sun, Y. (2015) · Signal Processing Image Communication · doi:10.1016/j.image.2015.01.005 · Cited by 8
“Compared with the results of the SR framework [15], our method obtains sharp edges in the final HR image using the proposed primitive structure prior even if there is insufficient good-quality HR examples to be found in the input image itself (within or across image scales).”
MethodResultInfluentialSelf-example based super-resolution with fractal-based gradient enhancement
Yu, L., Xu, Y. X., Xu, H., & Yang, X. (2013) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2013.6618442 · Cited by 8
“To take advantage of selfsimilarity, some recent works proposed to construct the example database from the input LR image itself[11, 12], which is promising to produce sharp and fine edges, but the wrongly hallucinated textures are meanwhile introduced.”
BackgroundMethodResultInfluentialNew adaptive interpolation scheme for image upscaling
Harb, S. M. E. B., Isa, N. A. M., & Salamah, S. A. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2647-9 · Cited by 8
“To overcome the shortcomings of the aforementioned methods, several adaptive methods, such as learning-based approaches [10, 11, 13, 35], reconstruction-based approaches [15, 29, 34], and adaptive interpolation-based approaches [3, 4, 7, 12, 14, 16, 20, 21, 33, 36–38, 40], have been recently introduced.”
MethodAhmad, T., & Quershi, S. S. (2010) · International Conference on Electronics and Information Engineering · doi:10.1109/iceie.2010.5559769 · Cited by 8
“A combined approach of both of them to achieve better SR results was also proposed in [6].”
BackgroundDictionary-based map compression for sparse feature maps
Tomomi, N., & Kanji, T. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5979638 · Cited by 8
“Repetitive patterns as well as self-similarity are inherent in natural scenes as well as man-made environments [21]- [24], and have been exploited by many computer vision approaches including image recognition [21], compression [22], completion [23] as well as super-resolution [24].”
BackgroundHardware implementation of real-time multiple frame super-resolution
Seyid, K., Blanc, S., & Leblebici, Y. (2015) · IFIP/IEEE International Conference on Very Large Scale Integration · doi:10.1109/vlsi-soc.2015.7314419 · Cited by 8
“[6] proposed a patch based SR resolution, which is database free single image super resolution.”
BackgroundSingle image super resolution with guided back-projection and LoG sharpening
Ngocho, B. M., & Mwangi, E. (2016) · IEEE Mediterranean Electrotechnical Conference (MELECON) · doi:10.1109/melcon.2016.7495419 · Cited by 8
“Irani and Peleg [20] proposed application of the method to super resolution from multiple images.”
MethodAchieving Super-Resolution With Redundant Sensing
Luu, D. K., Nguyen, A. T., & Yang, Z. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2885523 · Cited by 8
“tracted from numerous example data as utilized in many machine learning based methods [8], [10], [13]–[16].”
MethodSingle image super-resolution under multi-frame method
Zhu, S., & Li, Y. (2018) · Signal Image and Video Processing · doi:10.1007/s11760-018-1361-2 · Cited by 8
“The multi-frame SR method, firstly addressed in [4], often uses a set of LR images taken at the same scene to reconstruct the unknown HR image [5].”
MethodExample-based image super-resolution via blur kernel estimation and variational reconstruction
Yang, Q., Zhang, Y., & Zhao, T. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.12.008 · Cited by 8
Accelerate neural style transfer with super-resolution
Li, Z., Zhou, F., Yang, L., Li, X., & Li, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6929-x · Cited by 8
“Patch-based methods such as [3, 11, 12, 14, 44] can learn the mapping functions from paired LR and HR training images’ patches and the last category is sparse dictionary methods [32, 42, 43, 47].”
MethodImproving the Perceptual Quality of Document Images Using Deep Neural Network
Pandey, R. K., & Ramakrishnan, A. G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-22808-8_44 · Cited by 8
A novel singular value decomposition-based similarity measure method for non-local means denoising
Wang, Y., Song, X., Chen, K., Zhang, X., Tie, M., & Fang, H. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-01948-9 · Cited by 8
“NLM denoising is based on the assumption of self-similarity of the natural image: Similar patches recur many times in different spatial locations [31].”
BackgroundRes2NetFuse: A Novel Res2Net-based Fusion Method for Infrared and Visible Images
Xu, S., Xiao, Y., Li, H., Wu, X., Sun, J., & Palade, V. (2023) · International Conference on Machine Vision, Image Processing and Imaging Technology (MVIPIT) · doi:10.1109/mvipit60427.2023.00009 · Cited by 8
“Natural images inherently display robust predictive power [25] and significant internal data redundancy [26].”
BackgroundApproaching the Limit of Image Rescaling via Flow Guidance
Li, S., Zhang, G., Luo, Z., Liu, J., Zeng, Z., & Zhang, S. (2021) · British Machine Vision Conference (BMVC) · doi:10.5244/c.35.9 · Cited by 9
Single image super-resolution based on subpixel shifting model
Jeon, J., & Paik, J. (2015) · Optik · doi:10.1016/j.ijleo.2015.09.169 · Cited by 8
Adaptive joint nonlocal means denoising back projection for image super resolution
Gan, Z., Cui, Z., Chen, C., & Zhu, X. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738130 · Cited by 8
“Existing self similarity SR algorithms can be broadly categorized into two classes: within-scale based[3][8][11][12] and across-scale based [13][14][15] methods.”
MethodSuper Resolution by Comprehensively Exploiting Dependencies of Wavelet Coefficients
Kumar, N., & Sethi, A. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2729021 · Cited by 8
“Instead of using example LR-HR patch pairs sampled from several images, it has also been proposed to obtain these examples from multi-scale representations of the same image [6], [7].”
MethodLow - resolution vehicle recognition based on deep feature fusion
Xue, L., Zhong, X. R., Wang, R., Yang, J., & Hu, M. Q. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5940-6 · Cited by 8
“Generally, in the single frame image, we use interpolation to improve the resolution in the texture area [6].”
MethodFAST: Free Adaptive Super-Resolution via Transfer for Compressed Videos.Preprint
Zhang, Z., & Sze, V. (2016) · arXiv (Cornell University) · Cited by 8
Toward Real-World Super Resolution With Adaptive Self-Similarity Mining
Fan, Z., Yang, W., Guo, Z., & Liu, J. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3473320 · Cited by 9
Fast and detail-preserving low-dose CT denoising with diffusion model
Su, B., Dong, P., Hu, X., Wang, B., Zha, Y., Wu, Z., & Wan, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107580 · Cited by 9
Omni-Deblurring: Capturing Omni-Range Context for Image Deblurring
Li, Y., An, H., Zhang, T., Chen, X., Jiang, B., & Pan, J. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3549853 · Cited by 8
“The image’s internal statistics of patches recurrence [14], [55], which states that any small image patch in a natu-ral image recurs in smaller down-sampled versions of the image, is widely used in conventional image restoration [29].”
A Deep Learning Framework of Super Resolution for License Plate Recognition in Surveillance System
Tsai, P.-F., Shiu, J.-Y., & Yuan, S. (2025) · Mathematics · doi:10.3390/math13101673 · Cited by 9
Optimal filter based on scale-invariance generation of natural images
Jiang, F., Chen, B., Rho, S., Ji, W., Pan, L., Guo, H., & Zhao, D. (2015) · The Journal of Supercomputing · doi:10.1007/s11227-015-1398-8 · Cited by 7
Reduced-Reference Image Quality Assessment for Single-Image Super-Resolution Based on Wavelet Domain
Hu, Q., Sheng, Y., Yang, L., Li, Q., & Chai, L. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8833247 · Cited by 7
“The dataset consist of 30 HR images, 1620 SR images from 180 LR images using 9 different SR methods [11, 12, 13, 14, 15, 16] and the perceptual scores of 1620 SR images.”
MethodEbrahimi, M., & Bohun, C. S. (2020) · Communications in Nonlinear Science and Numerical Simulation · doi:10.1016/j.cnsns.2020.105508 · Cited by 7
Fast Non-Local Attention network for light super-resolution
Hong, J., Lee, B., Ko, K., & Ko, H. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.103861 · Cited by 7
SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering
Brahimi, M., Haefner, B., Yenamandra, T., Goldlüecke, B., & Cremers, D. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00311 · Cited by 10
“Different problem statements of SR lead to different approaches, e.g. the case of single image SR [12,19,38], video SR [7,8,20], or depth SR [16,45,46,56,62].”
BackgroundConvergence of various computer-aided systems for breast tumor diagnosis: a comparative insight
Singh, S. K., & Patnaik, K. S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19620-y · Cited by 8
“Bilinear interpolation [160], Nearest-Neighbor interpolation [161], and bicubic interpolation [162] are three of the most commonly used techniques for producing high-resolution (HR) images [163, 164].”
No-Clean-Reference Image Super-Resolution: Application to Electron Microscopy
Khateri, M., Ghahremani, M., Sierra, A., & Tohka, J. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3426349 · Cited by 9
“Itshould be noted that the developed theory and method are applicable to real EM datasets contaminated with real noises and corruptions without any reliance on specific noise assumptions, as we will validate through experiments using real EM datasets.”
BackgroundMethodOn Traffic Matrix Estimation via Super-Resolution and Federated Learning
Pappone, L., Sacco, A., & Esposito, F. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3516472 · Cited by 7
“…e.g., neighbor embedding [37], [38], [39], [40], sparse representation methods [41], [42], [43], [44], [45], clustered patch-spaces [46], image self-similarities [47], [48], and geometric transformations of patches in order to increase the number of examples and perform data augmentation [49].”
Multi-core token mixer: a novel approach for underwater image enhancement
Xu, T., Xu, S., Xue, C., Feng, C., & Li, H. (2025) · Machine Vision and Applications · doi:10.1007/s00138-024-01651-y · Cited by 9
Single-image superresolution of self-similar textures
Zachevsky, I., & Zeevi, Y. Y. J. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738197 · Cited by 7
“Single-image superresolution (SR) has attracted considerable attention in recent years [1] [2] [3] [4] [5] [6].”
Robust single-image super-resolution using cross-scale self-similarity
Salvador, J., Pérez-Pellitero, E., & Kochale, A. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025428 · Cited by 7
“Index Terms— Super-Resolution, Single-Image, Denoising, Self-Similarity, Multiscale Pyramid 1.”
Compact and coherent dictionary construction for example-based super-resolution
Bevilacqua, M., Roumy, A., Guillemot, C. M., & Morel, M.-L. A. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6638049 · Cited by 7
“On the other hand, the algorithm in [3] requires much higher computational times (see Table 2 in [6]).”
BackgroundMethodInfluentialSharpening Out of Focus Images using High‐Frequency Transfer
Tao, M. W., Malik, J., & Ramamoorthi, R. (2013) · Computer Graphics Forum · doi:10.1111/cgf.12069 · Cited by 7
Super-resolving a Single Intensity/Range Image via Non-local Means and Sparse Representation
Mandal, S., Bhavsar, A. V., & Sao, A. K. (2014) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/2683483.2683541 · Cited by 7
“Indeed, some works have been reported in the literature in the same direction [8, 20].”
BackgroundMethodImage super-resolution via 2D tensor regression learning
Yin, M., Gao, J., & Cai, S. (2014) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2014.11.005 · Cited by 7
“(a) Bicubic; (b) Chang’s [3]; (c) Yang’s [37]; (d) Glasner’s [14]; (e) O-SR (4); (f) R-SR (5); (g) NN-SR (6).”
MethodInfluentialGou, S., Liu, S., Wu, Y., & Jiao, L. (2015) · IET Image Processing · doi:10.1049/iet-ipr.2015.0046 · Cited by 7
Hidane, M., Gheche, M. E., Aujol, J., Berthoumieu, Y., & Deledalle, C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2571061 · Cited by 8
“In the context we were interested in, it was possible to perform a second scan, this time focusing on a specific part of the volume .”
BackgroundFace Hallucination and Recognition Using Kernel Canonical Correlation Analysis
Zhang, Z., Yuan, Y., Li, Y., Li, B., & Qiang, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70136-3_67 · Cited by 7
Super-Resolution on Degraded Low-Resolution Images Using Convolutional Neural Networks
Albluwi, F., Krylov, V. A., & Dahyot, R. (2019) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2019.8903000 · Cited by 7
“The example-based methods are categorised into two classes: internal example-based methods [6]–[8] and external example-based methods [9]–[14].”
MethodDeep Learning Based Super Resolution and Classification Applications for Neonatal Thermal Images
ŞENALP, F. M., & Ceylan, M. (2021) · Traitement du signal · doi:10.18280/ts.380511 · Cited by 7
Wang, C., Shen, Q., Wang, X., & Jiang, G. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116726 · Cited by 7
Image denoising via neighborhood-based multidimensional Gaussian process regression
Hua, T., Li, Q., Dai, K., Zhang, X., & Zhang, H. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02245-9 · Cited by 7
“For an image, the neighborhood of a pixel indicates the local feature it is embedded in and can be used for prediction in a regression-basedmodel [6].”
MethodRich feature distillation with feature affinity module for efficient image dehazing
Mitheran, S., Suresh, A., Nisha, J. S., & Gopi, V. P. (2022) · Optik · doi:10.1016/j.ijleo.2022.169656 · Cited by 7
“Various hand-crafted models were proposed [56, 57] to enable the restoration of HR images from their LR counterparts.”
MethodCross Spectral and Spatial Scale Non-local Attention-Based Unsupervised Pansharpening Network
Li, S., Tian, Y., Wang, C., Wu, H., & Zheng, S. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3278296 · Cited by 7
“Image patches tend to recur within and across scales of a same image, which is called the patch recurrence property [33], [34].”
BackgroundMethodYılmaz, V. (2023) · International Journal of Remote Sensing · doi:10.1080/01431161.2023.2234095 · Cited by 7
“The SR-D algorithm considers that patterns repeat themselves several times within an image, with fewer repetitions in areas that have high variance or more spatial details, which was also noted by Glasner, Bagon, and Irani (2009) and Vicinanza et al. (2015).”
Medical image super-resolution via transformer-based hierarchical encoder–decoder network
Sun, J., Zeng, X., Lei, X., Gao, M., Li, Q., Zhang, H., & Ba, F. (2024) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-024-00469-y · Cited by 8
Photo zoom: high resolution from unordered image collections
Eisemann, M., Eisemann, E., Seidel, H., & Magnor, M. A. (2010) · Cited by 7
Example-based super-resolution using self-patches and approximated constrained least squares filter
Cho, C., Jeon, J., & Paik, J. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025429 · Cited by 7
“Index Terms— Super-resolution, image restoration, selfexamples, stepwise degradation”
BackgroundSingle Image Super-Resolution Based on Local Self-Similarity
Lin, W.-T., & Lai, S. (2013) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2013.107 · Cited by 7
“Later, Glasner et al.[5] suggested to search exemplars in different scales of a given image without taking any extra information.”
BackgroundImage Super-Resolution Using Local Learnable Kernel Regression
Liao, R., & Qin, Z. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37431-9_27 · Cited by 7
“[5] raise the issue of patch redundancy in a single image.”
BackgroundMethodInfluentialRecursive MDL via graph cuts: Application to segmentation
Gorelick, L., Delong, A., Veksler, O., & Boykov, Y. Y. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126330 · Cited by 7
“resolution and de-noising [8], image re-targeting [2] and completion [18].”
BackgroundHybrid super resolution using refined face logs
Nasrollahi, K., & Moeslund, T. B. (2010) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2010.5586769 · Cited by 8
“The idea of using a hybrid super resolution system has been used previously by [13].”
BackgroundMethodInfluentialInter-Frame Information Transfer Via Projection Onto Convex Set for Video Deblurring
Huang, Y., & Fan, N. (2010) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2010.2060712 · Cited by 7
“It follows the dogma analogous to single-image-based super-resolution (SR) [1]: without example training images (i.”
BackgroundHybrid Example-Based Single Image Super-Resolution
Xian, Y., Yang, X., & Tian, Y. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27863-6_1 · Cited by 7
“Moreover, it is validated in [22] that average patch recurrence across scales decays as the resolution difference increases.”
BackgroundCombining self-learning based super-resolution with denoising for noisy images
Lee, O.-Y., Lee, J. W., & Kim, J. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.05.010 · Cited by 7
Single frame image super resolution via learning multiple ANFIS mappings
Yang, J., Shang, C., Li, Y., & Shen, Q. (2017) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee.2017.8015714 · Cited by 7
“Amongst various approaches, the single frame SR algorithms [1], [2], [3] have recently been increasingly gaining popularity.”
BackgroundComparison of Performance by Activation Functions on Deep Image Prior
Fujii, S., & Hayashi, H. (2019) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic.2019.8669063 · Cited by 7
Single Image Super-Resolution for Optical Satellite Scenes Using Deep Deconvolutional Network
Pendurkar, S., Banerjee, B., Saha, S., & Bovolo, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30642-7_37 · Cited by 7
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.