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 701–800 of 1,002
Maiseli, B. J., Wu, C. K., Mei, J., Liu, Q., & Gao, H. (2013) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2013.09.007 · Cited by 15
“Two main types of SR methods are known, namely classical multi-image SR, which involve reconstruction of a HR image from multiple LR images of the same scene but different sub-pixel alignment, and Example-Based SR, which deals with learning the correspondence between low and high resolution patches from a database [9].”
MethodWavelet-domain satellite image fusion based on a generalized fusion equation
Jin, B., Kim, G., & Cho, N. I. (2014) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.8.080599 · Cited by 15
“, blurred and downsampled) one.(7) This process is explained in Fig.”
BackgroundCapturing ground truth super-resolution data
Qu, C., Luo, D., Monari, E., Schuchert, T., & Beyerer, J. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532872 · Cited by 15
“As opposed to interpolation-based methods, SR is able to recover the missing high-frequency information in the original LR image by combining multiple images with sub-pixel shifts among them [1], or through inference of local HR structure from similar HR–LR pairs from external training data [2] or from the internal py…”
MethodFast Super-Resolution via Dense Local Training and Inverse Regressor Search
Pérez-Pellitero, E., Salvador, J., Torres‐Xirau, I., Ruiz‐Hidalgo, J., & Rosenhahn, B. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16811-1_23 · Cited by 15
“[6], presenting a powerful framework for fusing reconstruction-based and example-based SR.”
MethodExpanding Training Data for Facial Image Super-Resolution
Zeng, X., Huang, H., & Qi, C. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2655027 · Cited by 14
“’s [8], DPSR and SRCNN methods also produce high quality faces, but they bring subtle artifacts, e.”
BackgroundMethodInfluentialModified VDSR-based single image super-resolution using naturalness image quality evaluator
Çatalbaş, M. C. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-02005-1 · Cited by 14
“Figure 2 shows the illustration of SISR and multi-frame super-resolution (MFSR) [9, 16].”
BackgroundMethodYu, C., Hong, L., Pan, T., Li, Y., & Li, T. (2023) · Electronics · doi:10.3390/electronics12204235 · Cited by 14
Omnidirectional Image Super-resolution via Bi-projection Fusion
Wang, J.-G., Cui, Y., Li, Y., Ren, W., & Cao, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i6.28354 · Cited by 28
“As a typical low-level vision problem, super-resolution aims to generate high-resolution images with essential edge structures and texture details from low-resolution counter-parts (Glasner, Bagon, and Irani 2009).”
BackgroundDeep Internal Learning: Deep learning from a single input
Tirer, T., Giryes, R., Chun, S. Y., & Eldar, Y. C. (2024) · IEEE Signal Processing Magazine · doi:10.1109/msp.2024.3385950 · Cited by 16
“Real-world signals, such as images, possess re-curring patterns; see e.g. [36], [37].”
Video super resolution based on non-local regularization and reliable motion estimation
Lü, J., Zhang, H., & Sun, Y. (2014) · Signal Processing Image Communication · doi:10.1016/j.image.2014.01.002 · Cited by 15
“, real images usually show a high degree of redundancy by exhibiting numerous similar patterns [35]).”
BackgroundRobust Region Grouping via Internal Patch Statistics
Liu, X., Lin, L., & Yuille, A. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.252 · Cited by 14
“, texture synthesis [8], denoising [3], and super-resolution [10].”
BackgroundAntipodally Invariant Metrics for Fast Regression-Based Super-Resolution
Pérez-Pellitero, E., Salvador, J., Ruiz‐Hidalgo, J., & Rosenhahn, B. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2549362 · Cited by 16
“[6], presenting a powerful framework for fusing reconstruction-based and”
BackgroundTexture Reconstruction Guided by a High-Resolution Patch
Gheche, M. E., Aujol, J., Berthoumieu, Y., & Deledalle, C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2627812 · Cited by 18
“…[48], which uses the Wasserstein distance for comparing the histograms of the entire texture with a parametric model learned from the small patch, and introduces a preliminary step of dictionary learning for exploiting the given patch, in order to perform texture synthesis and image restoration.”
MethodMultiscale self-similarity and sparse representation based single image super-resolution
Xie, C., Zeng, W., Jiang, S., & Lu, X. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.03.073 · Cited by 14
“However, inspired by the observation that local patches in a natural image tend to redundantly appear many times inside the image not only within the current scale but also across multiple scales [36], we have every reason to believe that the capacity of NCSR model is limited as it fails to make full use of the redund…”
BackgroundDual-Streams Edge Driven Encoder-Decoder Network for Image Super-Resolution
Li, F., Bai, H., Zhao, L., & Zhao, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2846363 · Cited by 14
“In [13], based on the observation that patches in a natural image redundantly recur many times inside the image, Glasner et al.”
BackgroundProgram-Guided Image Manipulators
Zhang, X., Mao, J., Li, Y., Freeman, W. T., Tenenbaum, J. B., & Wu, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00413 · Cited by 25
Seismic data interpolation using deep internal learning
Wang, Q., Shen, Y., Fu, L., & Li, H. (2020) · Exploration Geophysics · doi:10.1080/08123985.2020.1748496 · Cited by 14
Deblurring Cataract Surgery Videos Using a Multi-Scale Deconvolutional Neural Network
Ghamsarian, N., Taschwer, M., & Schoeffmann, K. (2020) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi45749.2020.9098318 · Cited by 14
“It has been shown empirically [17] that most of the small patches (namely 5 × 5 or 7 × 7) in a naturally sharp image recur in its ideally down-sampled versions.”
BackgroundSaeed, K., Datta, S. C., & Chaki, N. (2020) · IEEE Access · doi:10.1109/access.2020.3006100 · Cited by 14
“Both of the images emerge within the same scale and across different scales as well [18].”
BackgroundDeepCFL: Deep Contextual Features Learning from a Single Image
Mastan, I. D., & Raman, S. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00294 · Cited by 18
“Deep feature learning captures good image features by using the strong internal data repetitions (self-similarity prior) [11, 15, 30, 42, 45], hand-crafted structure [7, 35], and explicit regularizer [21].”
BackgroundInferring High-Resolutional Urban Flow With Internet Of Mobile Things
Zhou, F., Jing, X., Li, L., & Zhong, T. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414134 · Cited by 14
Niaz, M. R., Ridwan, A. R., Wu, Y., Bennett, D. A. A., & Arfanakis, K. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2021.118869 · Cited by 14
“…low resolution images of the same object with slightly different perspectives ( Farsiu et al., 2004 ; Kim et al., 2015 ; Yuan et al., 2010 ), or from a single low resolution image ( Bevilacqua et al., 2012 ; Glasner et al., 2009 ; Ledig et al., 2016 ; Lim et al., 2017 ; Rueda et al., 2013 ).”
Super-resolution image visual quality assessment based on structure–texture features
Zhou, F., Wei, S., Lu, Z., Kang, B., Chen, M., & Qiu, G. (2023) · Signal Processing Image Communication · doi:10.1016/j.image.2023.117025 · Cited by 20
Single‐image super‐resolution with total generalised variation and Shearlet regularisations
Feng, W., & Lei, H. (2014) · IET Image Processing · doi:10.1049/iet-ipr.2013.0503 · Cited by 14
Self-similarity based image super-resolution on frequency domain
Park, S., Lee, O.-Y., & Kim, J. (2013) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2013.6694232 · Cited by 14
“In constructing the image pyramid for SR, it has been reported that an incremental coarse-grained method using a small scale factor produces a more elaborate result [4].”
BackgroundMethodEdge guided single depth image super resolution
Xie, J., Feris, R., & Sun, M. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025766 · Cited by 14
Multisensor Super Resolution Using Directionally-Adaptive Regularization for UAV Images
Kang, W., Yu, S., Ko, S., & Paik, J. (2015) · Sensors · doi:10.3390/s150512053 · Cited by 14
“Since the cubic-spline kernel performs low-pass filtering, it decreases the noise variance and guarantees searching sufficiently similar patches [8].”
BackgroundMethodSuper‐Resolution of Point Set Surfaces Using Local Similarities
Hamdi-Cherif, A., Digne, J., & Chaine, R. (2017) · Computer Graphics Forum · doi:10.1111/cgf.13216 · Cited by 14
Sex-classification from Cellphones Periocular Iris Images
Tapia, J. E., Arellano, C., & Viedma, I. A. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-26972-2_11 · Cited by 14
Noise-Robust Iterative Back-Projection
Yoo, J.-S., & Kim, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2940414 · Cited by 16
Mixed-dense connection networks for image and video super-resolution
Purohit, K., Mandal, S., & Rajagopalan, A. N. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.02.069 · Cited by 14
“Image patches tend to repeat in the image non-locally, and can provide useful information in terms of non-local prior to super-resolve an image [13, 2, 14, 3].”
BackgroundMulti-Stage Degradation Homogenization for Super-Resolution of Face Images With Extreme Degradations
Chen, L., Pan, J., Jiang, J., Zhang, J., Han, Z., & Bao, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3086595 · Cited by 14
High Resolution Millimeter Wave Imaging For Self-Driving CarsPreprint
Guan, J., Madani, S., Jog, S., & Hassanieh, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09579 · Cited by 17
“(c) Super-Resolution & Image Transformation: In computer vision, neural networks are used to increase the resolution of camera images and near-Infrared images [22, 24, 35, 58].”
BackgroundTwo-stage Network For Single Image Super-Resolution
Han, Y., Du, X., & Yang, Z. C. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00098 · Cited by 13
“In order to obtain a super-resolution image, [13] use the patch redundancy to produce.”
BackgroundMethodNeural Knitworks: Patched neural implicit representation networks
Czerkawski, M., Cardona, J., Atkinson, R. C., Michie, C., Andonović, I., Clemente, C., & Tachtatzis, C. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110378 · Cited by 18
“Patches have been identified as crucial representation features of image in various works [8, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29].”
BackgroundPost-trained convolution networks for single image super-resolution
Zandavi, S. M. (2023) · Artificial Intelligence · doi:10.1016/j.artint.2023.103882 · Cited by 15
Xiong, H., Gao, X., Zhang, N., He, H., Tang, W., Yang, Y., Chen, Y., Jiao, Y., Song, Y., & Yan, S. (2024) · Agriculture · doi:10.3390/agriculture14020318 · Cited by 13
“In recent developments, super-resolution techniques have been extensively applied to enhance the quality of low-resolution images, demonstrating significant potential in the field of agricultural disease identification and lesion counting [24–26].”
MethodChen, Q., Wen, W., & Qin, J. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106686 · Cited by 13
Context-aware single image super-resolution using locality-constrained group sparse representation
Tsai, C.-Y., Huang, D.-A., Yang, M.-C., Kang, L., & Wang, Y.-C. F. (2012) · Visual Communications and Image Processing · doi:10.1109/vcip.2012.6410851 · Cited by 13
“We apply the image pyramid used in [11] and learn context-specific image sparse representation for SR.”
MethodResultInfluentialSingle image super resolution via manifold linear approximation using sparse subspace clustering
Dang, C., Aghagolzadeh, M., Moghadam, A. A., & Radha, H. (2013) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2013.6737049 · Cited by 13
“Current state-of-the-art methods for image up-scaling can be loosely divided into two groups [12]: (i)”
BackgroundRegressor Basis Learning for anchored super-resolution
Agustsson, E., Timofte, R., & Gool, L. V. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900235 · Cited by 15
“Internal dictionary SR methods [10], [11] usually have high complexities since they need to extract and organize the data on-line from the input LR image.”
BackgroundMethodSuper-resolution for Selfie Biometrics: Introduction and Application to Face and Iris
Alonso‐Fernandez, F., Farrugia, R. A., Fiérrez, J., & Bigün, J. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-030-26972-2_5 · Cited by 16
Blind Separation of Ground-Roll Using Interband Morphological Similarity and Pattern Coding
Jia, Z., & Lu, W. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2980415 · Cited by 13
“Similar but not the same, in the area of natural image processing, self-similarity of images has been exploited for tasks, such as denoising and super-resolution [23]–[26].”
BackgroundJoint Sparse Representation-based Single Image Super-Resolution for Remote Sensing Applications
Deka, B., Mullah, H. U., Barman, T., & Datta, S. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3244069 · Cited by 13
Directional Super-Resolution by Means of Coded Sampling and Guided Upsampling
Schedl, D. C., Birklbauer, C., & Bimber, O. (2015) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2015.7168365 · Cited by 13
Document image super‐resolution using structural similarity and Markov random field
Chen, X., & Qi, C. (2014) · IET Image Processing · doi:10.1049/iet-ipr.2013.0412 · Cited by 13
“The other way is to generate pairs of HR and LR patches from the input image itself [32].”
BackgroundViewing-Distance Aware Super-Resolution for High-Definition Display
Shen, C.-T., Liu, H.-H., Yang, M., Hung, Y.-P., & Pei, S. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2375639 · Cited by 14
“8-10 show the super-resolution images by the proposed algorithm and the state-of-the-art methods.”
BackgroundMethodInfluentialWavelet Statistics of Sparse and Self-Similar Images
Fageot, J., Bostan, E., & Unser, M. A. (2015) · SIAM Journal on Imaging Sciences · doi:10.1137/151003015 · Cited by 13
“It is thus not surprising that numerous models driven by these observations have been used in various problems in image reconstruction [1, 6, 8, 20, 22, 33].”
BackgroundShu, Z., Xia, Y., & Zou, C. (2019) · Optik · doi:10.1016/j.ijleo.2019.04.005 · Cited by 13
Image super-resolution using TV priori guided convolutional network
Fu, B., Li, Y., Wang, X., & Ren, Y. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.06.022 · Cited by 13
Frequency Domain-Based Perceptual Loss for Super Resolution
Sims, S. D. (2020) · Machine learning for signal processing ... · doi:10.1109/mlsp49062.2020.9231718 · Cited by 13
“[3, 6, 7, 8, 9, 10, 11]), spanning back to at least the 1980s (ex.”
BackgroundZhou, D., Liu, Y., Li, X., & Zhang, C. (2020) · The Visual Computer · doi:10.1007/s00371-020-02007-z · Cited by 13
Super Resolution Reconstruction via Multiple Frames Joint Learning
Wang, P., Hu, X., Xuan, B., Mu, J., & Peng, S. (2011) · International Conference on Multimedia and Signal Processing (CMSP) · doi:10.1109/cmsp.2011.79 · Cited by 13
“To overcome the limitations of the reconstructed based algorithms, another category of methods [3], [4], [5] based on machine learning techniques have been proposed.”
MethodGPU accelerated high-quality video/image super-resolution
Zhao, Z., Song, L., Xie, R., & Yang, X. (2016) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb.2016.7521938 · Cited by 12
“Most recent state-of-the-art SR methods[1-8] are example-based solution that either use the internal similarities of input image or learn mapping functions from external low and high resolution data base.”
MethodJiao, J., Zhao, L., Pan, W., & Li, X. (2023) · Sensors · doi:10.3390/s23094189 · Cited by 13
“In addition, super-resolution algorithms and image enhancement algorithms can also be used to improve image resolution [84–86].”
MethodDeep Hyperspectral and Multispectral Image Fusion With Inter-Image Variability
Wang, X., Borsoi, R. A., Richard, C., & Chen, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3273118 · Cited by 19
“in single-image restoration algorithms [64].”
Meta-learning based blind image super-resolution approach to different degradations
Yang, Z., Xia, J., Li, S., Liu, W., Zhi, S., Zhang, S., Liu, L., Fu, Y., & Gündüz, D. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106429 · Cited by 12
Super-resolution of digital rock images with hybrid attention multi-branch neural network
Yang, Y., Wang, J., Liu, F., Zhang, L., Sun, H. X., Zhong, J., Zhang, K., & Yao, J. P. (2024) · Gas Science and Engineering · doi:10.1016/j.jgsce.2024.205395 · Cited by 16
Missing data super-resolution using non-local and statistical priors
Fablet, R., & Rousseau, F. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7350884 · Cited by 12
“Such pach-based techniques may be considered both for super-resolution [6, 13] and inpainting [3, 9] within different modeling framework, including learning-based regression [7], non-local means [13], Markov random fields [4, 6, 9].”
BackgroundMethodMulti-level Modified Finite Radon Transform Network for Image Upsampling
Zhao, Y. S., Wang, R., Wang, W., & Gao, W. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2504731 · Cited by 13
“In [20] and [21], the single-image local self-example-based methods were introduced by considering the similarities of local patches in different scales of the same image.”
MethodRobust Face Super-Resolution via Position Relation Model Based on Global Face Context
Chen, L., Pan, J., Jiang, J., Zhang, J., & Wu, Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3023580 · Cited by 12
“In the patch candidate refinement, the novel vision pattern priors, e.g. the contour feature [3], the self-similarity [14], the patch pattern expansion strategy [33], the HR information [29], and the color of the face [27] are proposed to further optimize the obtained patch candidate set.”
BackgroundScene Text Image Superresolution Through Multiscale Interaction of Structural and Semantic Priors
Zhu, Z., Lei, Z., Bai, Y., Wang, Y., & Li, P. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3375836 · Cited by 12
“ExistingSTISR technologies can be broadly classi fi ed into two main categories: traditional methods [1], [2], [3], and deep learning methods [4], [5], [6], [7].”
BackgroundHuang, C., Liang, Y., Ding, X., & Fang, C. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.11.042 · Cited by 12
Iterated neighbor-embeddings for image super-resolution
Türkan, M., Thoreau, D., & Guillotel, P. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025789 · Cited by 12
“(Top-row) Nearest-neighbor interpolation, bicubic interpolation, method in [9], method in [14]; (bottom-row) method in [15], method in [16], our method, and the original HR image.”
BackgroundMethodResultInfluentialImage super-resolution via a novel cascaded convolutional neural network framework
Zhang, F., Cai, N., Cen, G., Li, F., Wang, H., & Chen, X. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.01.009 · Cited by 13
Single image super-resolution via adaptive sparse representation and low-rank constraint
Li, X., Cao, G., Zhang, Y., & Wang, B. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.06.012 · Cited by 13
Cascaded Random Forests for Fast Image Super-Resolution
Liu, Z.-S., & Siu, W.-C. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451349 · Cited by 12
Zhang, X., He, J., Zeng, Q., & Shi, Z. (2019) · Atmosphere · doi:10.3390/atmos10050254 · Cited by 12
“For Equation (8), one key procedure is the determination of D and we attempt to recover high-resolution radar echo based on the nonlocal self-similarity [32] of the observed low-resolution radar echo.”
MethodExposure Interpolation Via Hybrid Learning
Zheng, C., Li, Z. G., Yang, Y., & Wu, S. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053741 · Cited by 12
“Deep learning methods usually outperform those conventional methods [8, 9, 10, 11].”
MethodRefining high-frequencies for sharper super-resolution and deblurring
Singh, V., Ramnath, K., & Mittal, A. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.103034 · Cited by 12
Super-Resolution using Deep Learning to Support Person Identification in Surveillance Video
Alkanhal, L., Alotaibi, D., Albrahim, N., Alrayes, S., Alshemali, G., & Bchir, O. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110749 · Cited by 13
“Recently, SISR systems using deep learning for both generic images and faces images enhancement have been reported in the literature [4][10] [11].”
BackgroundTudavekar, G., Patil, S. R., & Saraf, S. S. (2020) · CAAI Transactions on Intelligence Technology · doi:10.1049/trit.2019.0045 · Cited by 13
Super-Resolution Imaging Using Very Deep Convolutional Network in Terahertz NDT Field
Wang, Q., Zhou, H., Wang, Y., Xia, R., Liu, Q., Zhao, B., & Wang, Y. (2020) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd50554.2020.9261696 · Cited by 12
“As the most promising Terahertz technology, active Terahertz imaging [13] has been applied in Non-destructive testing (NDT) [4-5,14], security scanning [6-7] and other fields.”
MethodReducing magnetic resonance image spacing by learning without ground-truth
Xuan, K., Si, L., Zhang, L., Xue, Z., Jiao, Y., Yao, W., Shen, D. G., Wu, D., & Wang, Q. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108103 · Cited by 17
Single image super-resolution reconstruction based on fusion of internal and external features
Li, X., & Chen, Z. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11400-2 · Cited by 12
“[7] proposed to combine the idea of multi-image SR with instance-based SR to jointly develop repeated patches within and across image scales.”
BackgroundTask-Oriented Evaluation of Super-Resolution Techniques
Tian, L., Suzuki, A., & Koike, H. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.127 · Cited by 14
“A recent proposal [10] uses only a single image.”
BackgroundSeiler, J., Jonscher, M., Ussmueller, T., & Kaup, A. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2796725 · Cited by 12
“These algorithms exploit properties like self-similarity of the acquired object or scene [5] or use information from training data sets [6]–[8] for estimating a high-resolution image.”
MethodKim, S. Y., & Kim, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_24 · Cited by 12
Zoom in to the Details of Human-Centric Videos
Li, G., Zhao, Y., Ji, M., Yuan, X., & Fang, L. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190977 · Cited by 12
Lee, J., Cho, S.-H., & Kim, M. (2019) · arXiv (Cornell University) · Cited by 12
Orthogonally Regularized Deep Networks for Image Super-Resolution
Guo, T., Mousavi, H. S., & Monga, V. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462555 · Cited by 11
Intelligent diagnosis of flip chip solder joints with resolution enhanced SAM image
Lu, X., He, Z., Gutierrez, H. M., Liao, G., & Shi, T. (2023) · ISA Transactions · doi:10.1016/j.isatra.2023.02.014 · Cited by 11
Zhang, Q., Xu, X., Guo, Y., Lu, Y., He, Q., Pu, M., Li, X., Xu, M., Zhang, F., & Luo, X. (2025) · Nanophotonics · doi:10.1515/nanoph-2024-0600 · Cited by 12
“Although 4 × improvement in resolution has been realized in some studies [15], these approaches do not guarantee fidelity due to the fact that spatial high-frequency components cannot be recovered [16].”
Self-content super-resolution for ultra-HD up-sampling
Türkan, M., Thoreau, D., & Guillotel, P. (2012) · doi:10.1145/2414688.2414695 · Cited by 11
“Figure 8 demonstrates the results of koala image in comparison to the methods proposed in [13] and [9] when s = 3.”
BackgroundMethodInfluentialSubjective assessment of HDTV with superresolution function
Gohshi, S., Hiroi, T., & Echizen, I. (2014) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2014-11 · Cited by 11
“All of the SR proposals in the literature only include computer simulations and either do not work in real time or work only for a limited range of video sequence types [5-10,12-14].”
BackgroundHidden Relationships: Bayesian Estimation With Partial Knowledge
Michaeli, T., & Eldar, Y. C. (2011) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2011.2113343 · Cited by 11
Local- and holistic-structure preserving image super resolution via deep joint component learning
Shi, Y., Wang, K., Li, X., & Lin, L. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552908 · Cited by 12
Wu, H., Zhang, J., & Wei, Z. (2018) · IEEE Access · doi:10.1109/access.2018.2831791 · Cited by 11
SGCRSR: Sequential gradient constrained regression for single image super-resolution
Chen, H., He, X., Qing, L., Teng, Q., & Ren, C. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.04.012 · Cited by 11
Understanding Single Image Super-Resolution Techniques with Generative Adversarial Networks
Adate, A., & Tripathy, B. K. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1592-3_66 · Cited by 11
Learning Physical Parameters and Detail Enhancement for Gaseous Scene Design Based on Data Guidance
Li, C., Qiu, S., Wang, C., & Qin, H. (2020) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2020.2991217 · Cited by 13
“This work is also closely related to the image super-resolution (SR) [35] in computer vision, that generates a high-resolution image given a low-resolution input.”
BackgroundImage super-resolution using supervised multi-scale feature extraction network
Sun, Y., Zhang, Y., Liu, S., Lu, W., & Li, X. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09488-z · Cited by 11
“Early algorithms [9, 11] constructed LR-HR patch pairs based on the scale-space pyramid of LR image.”
MethodTraining-Free Deep Generative Networks for Compressed Sensing of Neural Action Potentials
Sun, B., Mu, C., Wu, Z., & Zhu, X. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3069436 · Cited by 11
“Several successful CS schemes are not directly based on generative models, but rely on structural assumptions about the signals, such as self-similarity in images for denoising [47] and super-resolution [48].”
BackgroundWang, B., Zou, Y. L., Zhang, L., Hu, Y. J., Yan, H. J., Zuo, C., & Chen, Q. (2021) · Photonics · doi:10.3390/photonics8080321 · Cited by 11
“With the development of deep learning methods, single image SR [9] has made significant progress.”
BackgroundHassan, M. A., Wang, Y., Pang, W., Wang, D., Li, D., Zhou, Y., & Xu, D. H. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.03.024 · Cited by 11
Disparity-constrained stereo endoscopic image super-resolution
Zhang, T., Gu, Y., Huang, X., Yang, J., & Yang, G. (2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02611-5 · Cited by 11
“To preserve the structure of the reconstructed HR images, patch-based approaches [8, 9] were proposed to learn the mapping between LR and HR images.”
MethodCapillaries segmentation of NIR-II images and its application in ischemic stroke
Hao, Y., Ji, A., Xing, R., Zhu, W., Jiang, B., Jian, Y., & Chen, H. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105742 · Cited by 11
Manuel, C. T., Zehnder, P., Kaya, S., Sullivan, R., & Hu, F. (2022) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2022.100148 · Cited by 11
Pal, D., Bose, S., More, D., Jha, A., Banerjee, B., & Jeppu, Y. (2023) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.08.004 · Cited by 11
ASFESRN: bridging the gap in real-time corn leaf disease detection with image super-resolution
Yeswanth, P. V., & Deivalakshmi, S. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01377-x · Cited by 11
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.