The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Super-resolution from a single image
Abstract
Methods for super-resolution can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose a unified framework for combining these two families of methods. We further show how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples). Our approach is based on the observation that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution. Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A Review of Image Denoising Algorithms, with a New One
Buades, A., Coll, B., & Morel, J. M. (2005) · Multiscale Modeling & Simulation · doi:10.1137/040616024 · Cited by 4,083 · cited 2×
“Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.”
BackgroundMethodTexture synthesis by non-parametric sampling
Efros, A. A., & Leung, T. K. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790383 · Cited by 3,023
Example-based super-resolution
Freeman, W. T., Jones, T. R., & Pasztor, E. C. (2002) · IEEE Computer Graphics and Applications · doi:10.1109/38.988747 · Cited by 2,498 · cited 5×
“In Fig. 7 we compare our method to results from [ 11 , 13] and [9].”
BackgroundResultInfluentialFast and Robust Multiframe Super Resolution
Farsiu, S., Robinson, M. D., Elad, M., & Milanfar, P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2004.834669 · Cited by 2,090 · cited 2×
“Recurrence of patches within the same image scale forms the basis for applying the Classical SR constraints to information from a single image (Sec.”
MethodImproving resolution by image registration
Irani, M., & Peleg, S. (1991) · CVGIP: Graphical Models and Image Processing · doi:10.1016/1049-9652(91)90045-l · Cited by 1,929 · cited 2×
“Recurrence of patches within the same image scale forms the basis for applying the Classical SR constraints to information from a single image (Sec.”
MethodSelf-citationFreeman, W. T., Pasztor, E. C., & Carmichael, O. T. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026501619075 · Cited by 1,459 · cited 2×
““Example-Based Super-Resolution” also termed “image hallucination” (introduced by [ 10 , 11, 2] and extended later by others e.g.”
BackgroundLimits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1033210 · Cited by 1,205
Limits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854852 · Cited by 1,184 · cited 2×
“Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution.”
InfluentialImage super-resolution using gradient profile prior
Sun, J., Xu, Z., & Shum, H.-Y. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587659 · Cited by 916 · cited 1×
“Sophisticated methods for image up-scaling based on learning edge models have also been proposed (e.g., [9, 19 ]).”
MethodGeneralizing the Nonlocal-Means to Super-Resolution Reconstruction
Protter, M., Elad, M., Takeda, H., & Milanfar, P. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.2008067 · Cited by 707 · cited 1×
“Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.”
Method
Research works printed but not linked: 2
- kim, 8, Example-based learning for single-image SR and JPEG artifact removal, MPI-TR
- efros, 1999, Texture synthesis by nonparametric sampling, ICCV
Cited by
Items 801–900 of 1,002
Single image super-resolution by combining self-learning and example-based learning methods
Ai, N., Peng, J., Zhu, X., & Feng, X. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2597-2 · Cited by 11
“It was also pointed out in [13] that by exploiting the Bscale invariant^ property [6], one can learn a dictionary pair directly from the given LR image itself.”
BackgroundAdaptive Charbonnier superresolution method with robust edge preservation capabilities
Maiseli, B. J., Liu, Q., Ogada, E. A., & Gao, H. (2013) · Journal of Electronic Imaging · doi:10.1117/1.jei.22.4.043027 · Cited by 11
“(3) to zero and embedding the resulting equation into a dynamical system, yields the evolution equation given by”
BackgroundSingle image super-resolution using adaptive domain transformation
Singh, A., & Ahuja, N. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738196 · Cited by 11
“One class of approaches tries to ‘hallucinate’ the missing information in the high resolution image using examples of pairs of low resolution (LR) and high resolution (HR) image patches, possibly using a training database [1, 2, 3], or using patches within the image [4, 5].”
BackgroundFablet, R., & Rousseau, F. (2016) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2016.2523605 · Cited by 11
“In the image processing field, image inpainting and superresolution have been particularly active research topics over the last decade [10], [14], [16], [31], [32].”
BackgroundA survey on inpainting techniques
Shivaranjani, S., & Priyadharsini, R. (2016) · International Conference on Electrical, Electronics, and Optimization Techniques · doi:10.1109/iceeot.2016.7755236 · Cited by 11
Piecewise linear regression-based single image super-resolution via Hadamard transform
Luo, J., Sun, X., Yiu, M. L., Jin, L., & Peng, X. (2018) · Information Sciences · doi:10.1016/j.ins.2018.06.030 · Cited by 11
“Interpolation-based methods [5, 20, 32, 38, 73], reconstruction-based methods [8, 10, 16, 28, 55, 72] and learning-based methods [7, 9, 11–15, 17, 18, 21–25, 27, 33, 34, 36, 37, 40 SC based methods [46, 58, 59, 65, 70] decompose an input LR image patch into a sparse linear combination of the atoms…”
MethodAre Recent SISR Techniques Suitable for Industrial Applications at Low Magnification?
Jia, W., Zhao, Y., Wang, R., Li, S., Min, H., & Liu, X. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2886792 · Cited by 11
“els have been proposed, such as neighbor-embedding-based methods [7], [8], sparse-representation-based methods [9]– [11], and local self-similarity-based methods [12].”
MethodRobust image retrieval by cascading a deep quality assessment network
Somasundaran, B. V., Soundararajan, R., & Biswas, S. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.115652 · Cited by 11
“[23] by exploiting the recurrence of patches in an image, both at the same scale as well as across scales.”
Hyperspectral Image Super-Resolution via Adaptive Dictionary Learning and Double ℓ 1 Constraint
Tang, S., Xu, Y., Huang, L., & Sun, L. (2019) · Remote Sensing · doi:10.3390/rs11232809 · Cited by 11
“On the other hand, due to the nonlocal correlations existing in natural images [41,42], the sparse coefficients are not randomly distributed.”
BackgroundEffectiveness of State-of-the-Art Super Resolution Algorithms in Surveillance Environment
Farooq, M. A., Khan, A. A., Ahmad, A., & Raza, R. H. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-74728-2_8 · Cited by 11
“It is a self-similarity based SR algorithm [8] that identifies relevant patches from the downscaled versions of the input image, and hence an external dictionary is not required.”
BackgroundMethodŞENALP, F. M., & Ceylan, M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11436-4 · Cited by 14
“In addition to all these studies, the super-resolution methods have wide range of applications, with the main applications being the development of satellite or aerial images [8], facial images [14], iris and eye images [32], print outs [11], sign or license plate information [11], and fingerprint images [42].”
BackgroundVideo Super-Resolution for Wireless Capsule Endoscopy Imaging Sensor
Zhou, C., Qiu, K., Chen, C., Zhang, D., & Guo, Y. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3193870 · Cited by 14
“may raise a question: can networks learn high-frequency information for large-size super-resolution from synthetic dataset with small sizes? Actually, a number of studies [20], [21] demonstrated the recurrence of small pieces of information (such as some repeat patterns) across scales within a single image.”
BackgroundSuper-resolution from a single image based on local self-similarity
Pan, L., Yan, W., & Zheng, H. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2834-8 · Cited by 11
“By using the new filters we designed, we search the matching patches only between the current level and its upper level, and the searching region is a small window in the current level image instead of the image pyramid which is used in [7, 12].”
BackgroundMethodResultInfluentialLi, D., Liu, Y., & Wang, Z. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296560 · Cited by 11
“With sufficient information in the external dataset or in the same input image across different scales [2, 3], example-based methods provide visually appealing results.”
MethodRobust Synthesis of Adversarial Visual Examples Using a Deep Image PriorPreprint
Gittings, T., Schneider, S. A., & Collomosse, J. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.01996 · Cited by 11
“The translation equivariance of CNNs enables DIP to exploit the internal recurrence of visual texture in images [12], in a similar way as the classical non-parametric patch based approaches to texture synthesis [8].”
MethodAlgorithms for super-resolution of images and videos based on learning methods
Bevilacqua, M. (2014) · theses.fr (ABES) · doi:10.70675/43559a3bz298az4282z9628zb3a3f1c1b218 · Cited by 11
“The method described in [58] paved the way to several SR algorithms (e.”
BackgroundMethodInfluentialNon-local self-attention network for image super-resolution
Zeng, K., Lin, H., Yan, Z., Fang, J., & Lai, T. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05343-y · Cited by 10
“Due to the self-similarity characteristics [19, 20] of the natural image which refers to the recurrence of image patches many times in the same image, the non-local dependency modeling of SA is crucial in SR and other low-level vision tasks [21–23].”
Single-sample image-fusion upsampling of fluorescence lifetime images
Kapitány, V., Fatima, A., Žičkus, V., Whitelaw, J., McGhee, E. J., Insall, R. H., Machesky, L. M., & Faccio, D. (2024) · Science Advances · doi:10.1126/sciadv.adn0139 · Cited by 11
“Self-similarity-based super-resolution [52] and self-supervised clustering [53] approaches offer an alternative to external training set, deriving statistical information for super-resolution from the very image that is up-sampled.”
BackgroundA Generic Multicorrespondence Matching Framework for Reference-Based Image Super-Resolution
Zheng, H., Heng, H., Yan, Z., Zeng, K., Fang, J., & Qiang, B. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3428600 · Cited by 11
“These matching-based methods tend to overlook the self-similarity [25], [26] of natural images, which has been proven to be effective for SISR [27].”
BackgroundRobust super-resolution in a multiview setup based on refined high-frequency synthesis
Richter, T., Seiler, J., Schnurrer, W., & Kaup, A. (2012) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2012.6343407 · Cited by 10
“Those two approaches are combined in [3] to create a SR image just by utilization of one single low-resolution image without any additional information.”
BackgroundFace super resolution based on parent patch prior for VLQ scenarios
Liang, C., Hu, R., Han, Z., Li, Q., & Lu, Z. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3611-z · Cited by 10
Real-Time Enhancement of Dynamic Depth Videos with Non-Rigid Deformations
Ismaeil, K. A., Aouada, D., Solignac, T., Mirbach, B., & Ottersten, B. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2622698 · Cited by 11
“proposed in [32] an adaptation of [33] to depth maps.”
BackgroundLin, Z., Jia, J., Gao, W., & Huang, F. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.05.050 · Cited by 10
Pansharpening Via Neighbor Embedding of Spatial Details
Liu, J., Zhou, C., Fei, R., Zhang, C., & Zhang, J. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3067877 · Cited by 10
“where the dictionary D is constructed at the reduced scale (RS) based on the scale invariance assumption [17], [61], and with”
MethodRao, B. J., Chakrapani, Y., & Kumar, S. S. (2021) · The Computer Journal · doi:10.1093/comjnl/bxab067 · Cited by 10
Hyperspectral image super-resolution reconstruction based on image partition and detail enhancement
Xu, Y., Lv, Y., Zhu, X., Liu, S., Sun, Y., & Wang, Y. (2022) · Soft Computing · doi:10.1007/s00500-022-07723-3 · Cited by 10
“As a result, HSI has been used for natural disaster warning [1], land cover identi cation [2], and change detection [3].”
MethodAutomatic Differentiation for Inverse Problems in X-ray Imaging and Microscopy
Guzzi, F., Gianoncelli, A., Billè, F., Carrato, S., & Kourousias, G. (2023) · Life · doi:10.3390/life13030629 · Cited by 10
“(iii) Example/patch-based algorithms [40] historically provided the best results from a purely aesthetic point of view [49]; the inner working relies on generating a self-dictionary of high-resolution patches, which can be used to generate an HR frame [50].”
BackgroundRelation-consistency graph convolutional network for image super-resolution
Yang, Y., Qi, Y., & Qi, S. (2023) · The Visual Computer · doi:10.1007/s00371-023-02805-1 · Cited by 11
“Tracing back to the early classical self-example studies [19,20], they captured self-similar patterns among the whole image to provide the relations between pixels in a global view, showing the sig-nificance of spatial relations in image SR field.”
Wang, Y., Lyu, B., Shi, C., & Hu, Y. (2023) · Georisk Assessment and Management of Risk for Engineered Systems and Geohazards · doi:10.1080/17499518.2023.2222383 · Cited by 10
Superresolution Image Reconstruction: Selective milestones and open problems
Li, X., Dong, W., Wu, J., Li, L., & Shi, G. (2023) · IEEE Signal Processing Magazine · doi:10.1109/msp.2023.3271438 · Cited by 13
“Note that SSEN can also take the input LR image as a self-reference, which is conceptually similar to the idea of self-similaritybased SISR [13].”
MethodKong, L., Wang, F., Yang, F., Leng, L., & Zhang, H. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15380-3 · Cited by 10
“With the third rise of deep learning, a large amount of neural network-based methods [5, 8, 10, 13, 19, 21, 22, 26–29 Currently, state-of-the-art methods for super-resolution are mostly based on deep learning, especially generative adversarial networks(GANs) [19, 27, 28].”
Zhang, W., Sun, R., Li, Z., Gao, L., Li, J., Zhao, B., & Zhang, B. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3459894 · Cited by 11
“Glasner et al. [31] extract the non-local patches across different resolution images to recover the HR images.”
BackgroundMi, Y., Chi, M., Zhang, Q., & Liu, P. (2024) · Scientific Reports · doi:10.1038/s41598-024-79777-2 · Cited by 12
A joint perspective towards image super-resolution: Unifying external- and self-examples
Wang, Z., Wang, Z., Chang, S., Yang, J., & Huang, T. S. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836048 · Cited by 10
“Given the smoothed patch X′ij , Freedman and Fattal [10] predict the missing highfrequency band of each unknown Xij , by first solving the following minimization (3): (m∗, n∗) = arg min(m,n)∈Wij ‖Y ′mn −X ′ij‖22, (3) where Wij is defined as a small searching window (e.g., 10 × 10) centered at ( is , j s ) on image Y ′.”
BackgroundMethodInfluentialNon-Additive Imprecise Image Super-Resolution in a Semi-Blind Context
Graba, F., Comby, F., & Strauss, O. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2621414 · Cited by 10
Depth image super-resolution via multi-frame registration and deep learning
Tseng, C. W., Su, H., Lai, S., & JenChi, L. (2016) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2016.7820834 · Cited by 10
“[8] used the self-similarity to increase the image resolution.”
MethodA regularized pan-sharpening approach based on self-similarity and Gabor prior
Upla, K. P., Joshi, M. V., & Khatri, N. L. (2017) · International Journal of Remote Sensing · doi:10.1080/01431161.2016.1274444 · Cited by 10
“Literature shows that on an average 23% best match patches (exactly same patches) are available across the image for a downsampling factor ( q ) of 2 (Glasner, Bagon, and Irani 2009; Khatri and Joshi 2013).”
BackgroundMethodJin, H. S., & Han, D. (2017) · Mathematical Problems in Engineering · doi:10.1155/2017/2048098 · Cited by 10
“In other words, there are fewer recurrences for zones characterized by a greater amount of spatial detail [21].”
BackgroundSingle image super-resolution with non-local balanced low-rank matrix restoration
You, X., Xue, W., Lei, J., Zhang, P., Cheung, Y., Tang, Y., & Zhou, N. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899809 · Cited by 10
MMSE-Directed Linear Image Interpolation Based on Nonlocal Geometric Similarity
Zhu, S., He, Z., Liu, S., & Zeng, B. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2711609 · Cited by 10
“, the nonlocal geometric similarity, used in our work helps collect similar image patches for the construction of a more reliable interpolation model, which also makes our proposed method quite different from the other nonlocal information based approaches [11]–[16].”
MethodLarge receptive field convolutional neural network for image super-resolution
Wang, Q., Fan, H., Cong, Y., & Tang, Y. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296423 · Cited by 10
“A category of SR approaches [2, 6, 14, 15, 13] learn a mapping between low/high-resolution patches.”
BackgroundSingle Image Super-Resolution Based on Improved WGAN
Yu, L., Long, X., & Tong, C. (2018) · International Conference on Advanced Control, Automation and Artificial Intelligence (ACAAI) · doi:10.2991/acaai-18.2018.24 · Cited by 10
Multiple Sequential Regularized Extreme Learning Machines for Single Image Super Resolution
Cosmo, D. L., & Salles, E. O. T. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2895543 · Cited by 10
“learning [11]–[13], multiple linear mappings [14]–[17], and deep learning [18]–[20].”
BackgroundExpression of Fractals Through Neural Network Functions
Dym, N., Sober, B., & Daubechies, I. C. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2991422 · Cited by 16
“Self similarity in images has been suggested as a tool for several tasks in computer vision including deblurring, dehazing and super resolution [3], [19], [25].”
MethodDing, N., Liu, Y., Fan, L., & Zhang, C. (2019) · Journal of Computer Science and Technology · doi:10.1007/s11390-019-1925-9 · Cited by 10
“Glasner et al.[33] found that local small paths recur frequently within the image itself and across-scales, called self-similarity, by which a unified framework combining the multi-image SR[34,35] and example-based SR was put forward.”
BackgroundMethodInfluentialMultiBoot Vsr: Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution
Kalarot, R., & Porikli, F. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00258 · Cited by 10
“The redundancy is often enforced in the form of local correlations by imposing sparsity constraints [27] or assuming constancy of various image statistics such as multi-scale patch recurrence [6] to recover lost high-frequency details.”
BackgroundMethodJoint Demosaicking and Blind Deblurring Using Deep Convolutional Neural Network
Chi, Z., Shu, X., & Wu, X. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803201 · Cited by 10
“In natural images, patch features often recur in different scales [11].”
BackgroundA Real-Time Super-Resolution Method Based on Convolutional Neural Networks
Fu, S., Lu, L., Li, H., Li, Z., Wu, W., Paul, A., Jeon, G., & Yang, X. (2019) · Circuits Systems and Signal Processing · doi:10.1007/s00034-019-01283-y · Cited by 10
“Recovering a high-resolution (HR) image based on a low-resolution (LR) image is referred as single-image super-resolution (SISR) [11,12].”
BackgroundInfluentialSun, W., & Chen, Z. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3142999 · Cited by 10
Stereo Cross Global Learnable Attention Module for Stereo Image Super-Resolution
Zhou, Y., Xue, Y., Deng, W., Nie, R., Zhang, J., Pu, J., Gao, Q., Lan, J., & Tong, T. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00146 · Cited by 10
“Self-similarity has achieved remarkable achievements in the field of image restoration [6,7,10].”
BackgroundSUMMARIZATION OF SURVEILLANCE VIDEO SEQUENCES USING FACE QUALITY ASSESSMENT
Nasrollahi, K., Moeslund, T. B., & Rahmati, M. (2011) · International Journal of Image and Graphics · doi:10.1142/s0219467811004068 · Cited by 10
On the statistics of natural stochastic textures and their application in image processing
Zachevsky, I., & Zeevi, Y. Y. J. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854721 · Cited by 10
“The proposed SR algorithm was evaluated on NST images and compared with a state-of-the-art, self-similarity-based single-image SR algorithm [20].”
MethodFractional-order bidirectional diffusion for image up-sampling
Ren, Z., He, C., & Li, M. (2012) · Journal of Electronic Imaging · doi:10.1117/1.jei.21.2.023006 · Cited by 10
Deep artifact-free residual network for single-image super-resolution
Nasrollahi, H., Farajzadeh, K., Hosseini, V., Zarezadeh, E., & Abdollahzadeh, M. (2019) · Signal Image and Video Processing · doi:10.1007/s11760-019-01569-3 · Cited by 10
“In internal examplebased algorithms, the self-similarity in images are utilized to construct LR-HR patch pairs [16-18].”
MethodNon-local attention association scheme for online multi-object tracking
Wang, H., Wang, S., Lv, J., Hu, C., & Li, Z. (2020) · Image and Vision Computing · doi:10.1016/j.imavis.2020.103983 · Cited by 11
Image Restoration by Deep Projected GSURE
Abu-Hussein, S., Tirer, T., Chun, S. Y., Eldar, Y. C., & Giryes, R. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00017 · Cited by 10
Internal Distribution Matching for Natural Image Retargeting.Preprint
Shocher, A., Bagon, S., Isola, P., & Irani, M. (2018) · arXiv (Cornell University) · Cited by 10
Self-citationSinIR : efficient general image manipulation with single image reconstruction
Yoo, J. (2021) · doi:10.14711/thesis-991012980219003412 · Cited by 10
Noise2Fast: Fast Self-Supervised Single Image Blind DenoisingPreprint
Lequyer, J., Philip, R., Sharma, A., & Pelletier, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10209 · Cited by 12
“It is also known, and is crucial to some super-resolution methods, that single images have a certain degree of self-similarity, and hence these patches also recur across scales [10, 11].”
BackgroundImage-Adaptive GAN based ReconstructionPreprint
Abu-Hussein, S., Tirer, T., & Giryes, R. (2019) · arXiv (Cornell University) · doi:10.1609/aaai.v34i04.5708 · Cited by 76
A survey of super-resolution image quality assessment
Shu, L., Zhu, Q., He, Y., Chen, W., & Yan, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.129279 · Cited by 16
Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution
Yang, C., Dong, R., Xiao, J., Zhang, C., Lam, K., Zhou, F., & Qiu, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3525900 · Cited by 10
“Self-similarity is essential because it significantly contributes to the reconstruction of HR images [13], [14], [15], [16].”
Zhou, X., Shi, P., & Xu, X. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103482 · Cited by 10
Oz, N., Sochen, N., David Mendlovic, B., & Klapp, I. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110765 · Cited by 10
Huo, Y., Gang, S., Xiao, X., Fu, B., & Sun, X. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02245-z · Cited by 9
Color image enhancement of low-resolution images captured in extreme lighting conditions
Krieger, E. W., Asari, V. K., & Arigela, S. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2050716 · Cited by 9
Augmented Coupled Dictionary Learning for Image Super-Resolution
Rushdi, M. A., & Ho, J. C. F. (2012) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2012.52 · Cited by 9
“Example-based techniques learn the mapping between the low- and high-resolution patches from a training dataset and apply this mapping to low-resolution patches of test images [3], [4].”
BackgroundGedkhaw, E., & Ketcham, M. (2019) · Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) · doi:10.1109/ri2c48728.2019.8999891 · Cited by 9
DRCS-SR: Deep Robust Compressed Sensing for Single Image Super-Resolution
Kasem, H. M., Selim, M. M., Mohamed, E. M., & Hussein, A. H. (2020) · IEEE Access · doi:10.1109/access.2020.3024164 · Cited by 9
“…have been utilized in SISR computer vision task, including prediction-based methods [5]–[7], edge-based methods [8], [9], statistical methods [10], [11], patch-based methods [12], [13], missing data reconstruction in remote sensing image [14]–[16],and sparse representation methods [10], [17].”
MethodYin, Z., Li, X., Ge, Y., Shang, C., Li, X., Du, Y., & Ling, F. (2021) · The Cryosphere · doi:10.5194/tc-15-2835-2021 · Cited by 9
Cascade Attention Blend Residual Network For Single Image Super-Resolution
Chen, T., Xiao, G., Tang, X., Han, X.-F., Ma, W., & Gou, X. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506151 · Cited by 9
“Single image super-resolution (SISR) [1] reconstruction has been intensively used for image quality improvement of low-resolution images, for example in medical or multimedia research, as a supplement for the unsatisfactory requirement of imaging facility.”
BackgroundMathur, P., Singh, A., Azeemuddin, S., Adoni, J., & Adireddy, P. (2021) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss52988.2021.9663831 · Cited by 9
Super Resolution for Noisy Images Using Convolutional Neural Networks
Mushtaq, Z. B., Nasti, S. M., Verma, C., Raboacă, M. S., Kumar, N., & Nasti, S. J. (2022) · Mathematics · doi:10.3390/math10050777 · Cited by 9
NMR Relaxation Modelling in Porous Media with Dual-Scale-Resolved Internal Magnetic Fields
Cui, Y., Shikhov, I., & Arns, C. H. (2022) · Transport in Porous Media · doi:10.1007/s11242-022-01752-0 · Cited by 9
Recurrent Large Kernel Attention Network for Efficient Single Infrared Image Super-Resolution
Liu, G., Zhou, S., Chen, X., Yue, W., & Ke, J. (2023) · IEEE Access · doi:10.1109/access.2023.3344830 · Cited by 9
“Single-image super-resolution is a classical computer vision problem, which reconstruct a high-resolution image from an LR image by solving an ill-posed inverse problem [3], [4], [5].”
BackgroundColorization for Single Image Super Resolution
Liu, S., Brown, M. S., Kim, S. J., & Tai, Y. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15567-3_24 · Cited by 9
“Hybrid approaches that combine elements of reconstruction and learning based methods have also been proposed (e.g., [22, 23 ]).”
MethodLimitation of Super Resolution Image Reconstruction for Video
Gohshi, S. (2013) · International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN) · doi:10.1109/cicsyn.2013.24 · Cited by 9
“The result resolution of SRR depends on the characteristics of the LPF and it is necessary for LRIs to have aliasing signal [2][5].”
BackgroundDynamic super resolution of depth sequences with non-rigid motions
Ismaeil, K. A., Aouada, D., Mirbach, B., & Ottersten, B. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738136 · Cited by 9
“As a solution to these major limitations, example-based SR algorithms have been proposed [4], as well as their combinations with classical multi-frame SR [5].”
Hybrid Video Compression Using Selective Keyframe Identification and Patch-Based Super-Resolution
Glaister, J., Chan, C., Frankovich, M., Tang, A., & Wong, A. M. (2011) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2011.25 · Cited by 9
“In single frame super-resolution algorithms, details are enhanced by finding spatial redundancies [2] and in multiframe super-resolution schemes, multiple images are used to enhance detail through temporal and spatial redundancies [3].”
BackgroundImage super-resolution via feature-based affine transform
Hsu, C., & Lin, C. (2011) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2011.6093845 · Cited by 9
Enlargement of Image Based Upon Interpolation Techniques
Reddy, K., & Reddy, K. R. (2013) · Cited by 9
A Taxonomy of Example-Based Super Resolution
Salvador, J. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-809703-8.00002-2 · Cited by 11
Hyperspectral image super‐resolution under misaligned hybrid camera system
Lin, Y., Zheng, Y., Fu, Y., & Huang, H. (2018) · IET Image Processing · doi:10.1049/iet-ipr.2017.1340 · Cited by 9
Sparse multi-modal probabilistic latent semantic analysis for single-image super-resolution
Fernández-Beltrán, R., & Pla, F. (2018) · Signal Processing · doi:10.1016/j.sigpro.2018.05.026 · Cited by 9
“For example, the work presented in [14] approximates the blur operator by a Gaussian kernel and the patch redundancy is carried out by an approximation of the nearest neighbour search.”
MethodScale-Recurrent Multi-residual Dense Network for Image Super-Resolution
Purohit, K., Mandal, S., & Rajagopalan, A. N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_9 · Cited by 9
Relation-Aware Global Attention.
Zhang, Z., Lan, C., Zeng, W., Jin, X., & Chen, Z. (2019) · Cited by 9
WITHDRAWN: Residual Dense Convolutional Neural Network for Image Super-Resolution
Abbass, M. Y. (2020) · Optik · doi:10.1016/j.ijleo.2020.165341 · Cited by 9
Progressive Attentional Learning for Underwater Image Super-Resolution
Chen, X., Wei, S., Yi, C., Quan, L., & Lu, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66645-3_20 · Cited by 9
Single Image Super-resolution Model Based on Improved Sub-pixel Convolutional Neural Network
Jiang, P., Lin, W., & Shang, W. (2021) · 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA) · doi:10.1109/icpeca51329.2021.9362548 · Cited by 9
“According to the principle of the algorithm, it can be divided into three main categories: super-resolution algorithms based on interpolation, reconstruction, and learning[8,9,10,2].”
BackgroundGenerative adversarial image super‐resolution network for multiple degradations
Lin, H., Fan, J., Zhang, Y., & Peng, D. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2020.1176 · Cited by 9
“Image SR is a seriously ill-posed inverse problem, so the prior information of images is learned from low-resolution (LR) and high-resolution (HR) samples [2, 3] plays an indispensable role in recovering details from LR images.”
BackgroundCross-Dimension Attention Guided Self-Supervised Remote Sensing Single-Image Super-Resolution
Jiang, W., Zhao, L., Wang, Y., Liu, W., & Liu, B. (2021) · Remote Sensing · doi:10.3390/rs13193835 · Cited by 9
“The cross-scale recurrence of small pieces of information in a single image has proven to be a very powerful feature of natural images [26,34].”
BackgroundPatch-based stochastic attention for image editing
Cherel, N., Almansa, A., Gousseau, Y., & Newson, A. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103866 · Cited by 13
“Self-similarity has also been identified as a key component for single-image super-resolution (Glasner et al., 2009; Michaeli and Irani, 2014).”
BackgroundImage Super-Resolution: Use of Self-learning and Gabor Prior
Khatri, N. L., & Joshi, M. V. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37431-9_32 · Cited by 9
Accelerating single-image super-resolution polynomial regression in mobile devices
Amanatiadis, A. A., Bampis, L., & Gasteratos, A. C. (2015) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2015.7064112 · Cited by 9
“Machine learning superresolution, 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 realtime applications.”
BackgroundAntialiased super-resolution with parallel high-frequency synthesis
Jiang, X., Sheng, B., Lin, W., Li, P., Ma, L., & Shen, R. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-3049-8 · Cited by 9
“5 A Comparison between stare-of-art methods and ours: a ground truth, b result by [8], c result by [5] d result by [9], e result by [7], f result by [41], e our result”
BackgroundRolling Shutter Super-Resolution
Punnappurath, A., Rengarajan, V., & Rajagopalan, A. N. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.71 · Cited by 9
“3(c), (d) and (e) are the outputs of state-of-the-art single image SR methods [7], [19], and [21], respectively.”
BackgroundInfluentialDepth map upsampling by self-guided residual interpolation
Konno, Y., Tanaka, M., Okutomi, M., Yanagawa, Y., Kinoshita, K., & Kawade, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899832 · Cited by 9
“[20] proposed upsampling by a gradual refinement in the small upsampling factor.”
BackgroundUnsupervised Single-Image Super-Resolution with Multi-Gram Loss
Shi, Y., Li, B., Wang, B., Qi, Z., & Liu, J. (2019) · Electronics · doi:10.3390/electronics8080833 · Cited by 9
“In the realm of SR, there are mainly three distinct regimes: interpolation-based methods [23,24], reconstruction-based methods [25], and pairs-learning-based methods [1–5, 7 , 11, 20, 26 Supervised SR methods.”
BackgroundMethodInfluentialFarrugia, R. A., & Guillemot, C. M. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.115638 · Cited by 9
Fast Generation of High-Fidelity RGB-D Images by Deep Learning With Adaptive Convolution
Xian, C., Zhang, D., Dai, C., & Wang, C. C. L. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3002069 · Cited by 9
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.