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 401–500 of 1,002
MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution
Li, J., Chen, C., Cheng, Z., & Xiong, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19797-0_14 · Cited by 39
“Examplar-based methods leverage a dataset of LR-HR image patch pairs [13,14,43,59,60], or exploit self-similarity inside the LR image [16,62].”
MethodGlobal-Local Face Upsampling NetworkPreprint
Tuzel, O., Taguchi, Y., & Hershey, J. R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.07235 · Cited by 46
“To invert the under-determined system, local constraints are enforced as priors based on image statistics [3,4,5] and exemplar patches [6,7,8].”
MethodInGAN: Capturing and Remapping the "DNA" of a Natural ImagePreprint
Shocher, A., Bagon, S., Isola, P., & Irani, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00231 · Cited by 53
“This observation was empirically verified by [6, 23].”
Self-citationSingle image super-resolution by approximated Heaviside functions
Deng, L.-J., Guo, W., & Huang, T. (2016) · Information Sciences · doi:10.1016/j.ins.2016.02.015 · Cited by 38
Context Adaptive Network for Image Inpainting
Deng, Y., Hui, S., Zhou, S., Huang, W., & Wang, J. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3298560 · Cited by 43
“Whereas the source of these methods, patch-based techniques, has been shown in the literature [55], [56], [57] that cross-scale similarity can bring impressive performance benefits.”
BackgroundDual-sparsity regularized sparse representation for single image super-resolution
Li, J., Gong, W., & Li, W. (2014) · Information Sciences · doi:10.1016/j.ins.2014.11.032 · Cited by 38
Super-Resolution Reconstruction Using Cross-Scale Self-similarity in Multi-slice MRI
Plenge, E., Poot, D. H. J., Niessen, W. J., & Meijering, E. H. W. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40760-4_16 · Cited by 38
“A common feature of these example-based methods is the formulation of a parent-child structure in which the “nearest-neighbor” of an input LR-patch is sought among the LR-parents of HR-child-patches in either a database [3] or in the image itself [7].”
MethodImage Super-Resolution with Deep Dictionary
Maeda, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19800-7_27 · Cited by 46
Learning a Mixture of Deep Networks for Single Image Super-Resolution
Liu, D., Wang, Z., Nasrabadi, N. M., & Huang, T. S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54187-7_10 · Cited by 41
“A large number of single image SR methods have been proposed in the literature, including interpolation based method [2], edge model based method [3] and example based method [4,5,6,7,8,9].”
MethodContour Stencils: Total Variation along Curves for Adaptive Image Interpolation
Getreuer, P. (2011) · SIAM Journal on Imaging Sciences · doi:10.1137/100802785 · Cited by 37
“Recently, these works have inspired several nonlocal interpolation methods [16, 25, 35, 45, 47].”
BackgroundSuper-Interpolation With Edge-Orientation-Based Mapping Kernels for Low Complex Upscaling
Choi, J.-S., & Kim, M. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2507402 · Cited by 37
“Many example-based SR methods [16]–[21], [27]–[29] employ one of the following two algorithms to reconstruct HR patches from LR patches, as stated in [28]: - Neighbor embedding (NE): LR patches similar to the”
MethodSparsity-Based Color Image Super Resolution via Exploiting Cross Channel Constraints
Mousavi, H. S., & Monga, V. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2704443 · Cited by 38
“[8] used 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 and approached the single image super resolution problem.”
MethodTerrain Super‐resolution through Aerial Imagery and Fully Convolutional Networks
Argudo, O., Chica, A., & Andújar, C. (2018) · Computer Graphics Forum · doi:10.1111/cgf.13345 · Cited by 46
Chen, H., Zhang, X., Liu, Y., & Zeng, Q. (2019) · Atmosphere · doi:10.3390/atmos10090555 · Cited by 38
“Since the weather radar echo degradation process, as shown in Figure 1, is ill-defined and irreversible, and that the point spread functions for different imaging systems are different, a Gaussian filter is usually used to simulate the process of the degradation of radar echo [9,15,30,46,47].”
MethodAIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
Wei, P., Lu, H., Timofte, R., Lin, L., Zuo, W., Pan, Z., Li, B., Xi, T., Fan, Y., Zhang, G., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-67070-2_24 · Cited by 48
Neural architecture search for deep image prior
Ho, K., Gilbert, A., Jin, H., & Collomosse, J. P. (2021) · Computers & Graphics · doi:10.1016/j.cag.2021.05.013 · Cited by 46
Invertible Rescaling Network and Its Extensions
Xiao, M., Zheng, S., Liu, C., Lin, Z., & Liu, T. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01688-4 · Cited by 38
“SR works focus on mitigating the inherent ill-posed problem by learning strong prior information by example-based strategy (Freedman & Fattal, 2011; Glasner et al., 2009b; Kim & Kwon, 2010; Schulter et al., 2015) or deep learning models (Dai et al., 2019; Dong et al., 2015; Guo et al., 2020; Lim et…”
BackgroundMethodA Fully Progressive Approach to Single-Image Super-ResolutionPreprint
Wang, Y., Perazzi, F., McWilliams, B., Sorkine‐Hornung, A., Sorkine‐Hornung, O., & Schroers, C. (2018) · arXiv (Cornell University) · doi:10.3929/ethz-b-000321437 · Cited by 37
Hyperspectral Image Super-Resolution Network Based on Cross-Scale Nonlocal Attention
Li, S., Tian, Y., Wang, C., Wu, H., & Zheng, S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3269074 · Cited by 40
“In the pioneering study, Glasner et al. [50] integrated the methods of multiple images SR and example-based SR to exploit repeating patches within and across multiscales of the image.”
BackgroundMethodTranslation-Symmetry-Based Perceptual Grouping with Applications to Urban Scenes
Park, M., Brocklehurst, K., Collins, R. T., & Liu, Y. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19318-7_26 · Cited by 36
“Recurrence of similar patches in an image forms the basis for their single view super-resolution approach in [25], and therefore correctly identifying corresponding patches is very important in this.”
BackgroundInfluentialLearning-based image super-resolution using weight coefficients of synaptic connections
Izonin, I., Tkachenko, R., Peleshko, D., Рак, Т., & Batyuk, D. (2015) · IEEE International Conference on Computer Sciences and Information Technologies (CSIT) · doi:10.1109/stc-csit.2015.7325423 · Cited by 36
“In general, there are many algorithms [1, 2, 8, 10-19] for changing the resolution, depending on the purpose of the artificial intelligence systems.”
MethodRAW Image Reconstruction Using a Self-Contained sRGB-JPEG Image with Only 64 KB Overhead
Nguyen, R. M. H., & Brown, M. S. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.183 · Cited by 36
“Representative work include interpolation-based methods [15, 29], edge-based methods [6, 9, 27], and example-based methods [11, 12].”
MethodImagining the Unimaginable Faces by Deconvolutional Networks
Yu, X., & Porikli, F. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2808840 · Cited by 36
“The first group of methods [28], [32], [33], [30] exploit self-similarity of patches in the input image.”
MethodKrig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_2 · Cited by 44
Crop Disease Classification on Inadequate Low-Resolution Target Images
Wen, J., Shi, Y., Zhou, X., & Xue, Y. (2020) · Sensors · doi:10.3390/s20164601 · Cited by 36
“Image SR methods aim to recover detailed and spatial HR images from the corresponding LR images [25].”
MethodInterest Point Detector and Feature Descriptor Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_6 · Cited by 44
A Fuzzy-Rule-Based Approach for Single Frame Super Resolution
Purkait, P., Pal, N. R., & Chanda, B. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2312289 · Cited by 35
Noise adaptive super-resolution from single image via non-local mean and sparse representation
Mandal, S., Bhavsar, A. V., & Sao, A. K. (2016) · Signal Processing · doi:10.1016/j.sigpro.2016.09.017 · Cited by 35
An Integrated Dictionary-Learning Entropy-Based Medical Image Fusion Framework
Qi, G., Wang, J., Zhang, Q., Zeng, F., & Zhu, Z. (2017) · Future Internet · doi:10.3390/fi9040061 · Cited by 35
“Sparse-representation is widely applied to image denoising [10], image deblurring [11], image inpainting [12], super-resolution [13], and image fusion [14,15].”
BackgroundHigh-frequency details enhancing DenseNet for super-resolution
Zhou, F., Li, X., & Li, Z. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.02.027 · Cited by 35
Multi-focus Image Fusion using Fully Convolutional Two-stream Network for Visual Sensors
Xu, K., Qin, Z., Wang, G., Zhang, H., Huang, K., & Ye, S. (2018) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2018.05.019 · Cited by 35
“The same phenomenon is also described in [18-33], where increase of layers leads to speed sacrifice and performance degradation for image restoration.”
BackgroundChannel Attention and Multi-level Features Fusion for Single Image Super-Resolution
Lu, Y., Zhou, Y., Jiang, Z., Guo, X., & Yang, Z. (2018) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2018.8698663 · Cited by 35
Remote sensing images super-resolution with deep convolution networks
Ran, Q., Xu, X., Zhao, S., Li, W., & Du, Q. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7091-1 · Cited by 35
“Motivated by recent compressive sensing theories [3] and sparsity prior, sparse coding super-resolution (SCSR) was presented in [10].”
Single-Image super-resolution - When model adaptation matters
Liang, Y., Timofte, R., Wang, J., Zhou, S., Gong, Y., & Zheng, N. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107931 · Cited by 39
3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution
Zhang, H., Shinomiya, Y., & Yoshida, S. (2021) · Sensors · doi:10.3390/s21092978 · Cited by 36
“Initially, SISR used a form of regularization conditions and then used prior knowledge to enhance the reconstruction ability of linear models [11].”
BackgroundMethodInfluentialExtracting a Good Quality Frontal Face Image From a Low-Resolution Video Sequence
Nasrollahi, K., & Moeslund, T. B. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2162267 · Cited by 35
“However, unlike RBSR algorithms there is no guarantee that the hallucinated HR [20].”
BackgroundLi, D., & Harris, J. M. (2018) · Geophysical Journal International · doi:10.1093/gji/ggy380 · Cited by 37
“2007), image restoration and super-resolution tasks (Dong et al. 2011; Glasner et al. 2009; Huang et al. 2015).”
DASR: Dual-Attention Transformer for infrared image super-resolution
Liang, S., Song, K., Zhao, W., Li, S., & Yan, Y. (2023) · Infrared Physics & Technology · doi:10.1016/j.infrared.2023.104837 · Cited by 35
Arbitrary-scale Super-resolution via Deep Learning: A Comprehensive Survey
Liu, H., Li, Z., Shang, F., Liu, Y., Wan, L., Feng, W., & Timofte, R. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102015 · Cited by 50
Li, Z., Teng, Q., He, X., Yue, G., & Wang, Z. (2017) · Journal of Applied Geophysics · doi:10.1016/j.jappgeo.2017.04.013 · Cited by 34
Efficient super-resolution algorithm using overlapping bicubic interpolation
Ruangsang, W., & Aramvith, S. (2017) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2017.8229459 · Cited by 34
“Single image SR [2] is the method to increase resolution from only single image LR input.”
MethodImage Super-Resolution With Self-Similarity Prior Guided Network and Sample-Discriminating Learning
Hu, Y., Li, J., Huang, Y., & Gao, X. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3093483 · Cited by 36
Super-resolution reconstruction of brain magnetic resonance images via lightweight autoencoder
Andrew, J., Mhatesh, T. S. R., Sebastin, R. D., Sagayam, K. M., Jennifer Eunice, R., Pomplun, M., & Dang, H. (2021) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100713 · Cited by 38
Multi-Resolution Data Fusion for Super-Resolution Electron Microscopy
Sreehari, S., Venkatakrishnan, S. V., Bouman, K. L., Simmons, J. P., Drummy, L. F., & Bouman, C. A. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.146 · Cited by 36
“For these reasons, there is growing interest in reconstructing full-resolution images from sparsely-sampled [1, 15, 22] and low-resolution images [11, 14, 18, 20].”
BackgroundImage super-resolution with densely connected convolutional networks
Kuang, P., Ma, T., Chen, Z., & Li, F. (2019) · Applied Intelligence · doi:10.1007/s10489-018-1234-y · Cited by 33
“Unlike the example-based methods, it focuses on learning a proper mapping function from the connections between LR images and HR images by using auxiliary data which could be collected either from input LR image itself directly [1, 3, 7], or from fruitful natural images indirectly [8–11].”
BackgroundMethodSemantic super-resolution: When and where is it useful?
Timofte, R., Smet, V. D., & Gool, L. V. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.09.008 · Cited by 34
Dual-Geometric Neighbor Embedding for Image Super Resolution With Sparse Tensor
Yang, S., Wang, Z., Zhang, L., & Wang, M. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2319742 · Cited by 33
“IN THE last decade, there have increasing interests in synthesizing a new High-Rresolution (HR) image by using one Low-Resolution (LR) image and a set of examples [1], including k-nearest neighbors synthesis algorithms [2]–[6], sparse coding algorithms [7]–[11], sparse regression algorithms [12]–[14], self-similarity…”
A performance comparison among different super-resolution techniques
Thapa, D., Raahemifar, K., Bobier, W. R., & Lakshminarayanan, V. (2015) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2015.09.011 · Cited by 33
“[83] introduced a unified method for combining both reconstruction-based and learning-based SR.”
MethodCollaborative Representation Cascade for Single-Image Super-Resolution
Zhang, Y., Zhang, Y., Zhang, J., Xu, D., Fu, Y., Wang, Y., Ji, X., & Dai, Q. (2017) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2705480 · Cited by 34
“Under the notion of internal example-based method [43], Cui et al.”
MethodPerception-driven semi-structured boundary vectorization
Hoshyari, S., Dominici, E. A., Sheffer, A., Carr, N., Wang, Z., Ceylan, D., & Shen, I. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201312 · Cited by 40
“Image upscaling or super-resolution methods increase the resolution of input images [Dahl et al. 2017; Dong et al. 2014; Fattal 2007; Glasner et al. 2009; Hou and Andrews 1978; Kim et al. 2016; Li and Orchard 2001; Nasrollahi and Moeslund 2014; Wang et al. 2015; Yang et al. 2014].”
MethodImagePairs: Realistic Super Resolution Dataset via Beam Splitter Camera Rig
Joze, H. R. V., Zharkov, I., Powell, K. D., Ringler, C., Liang, L., Roulston, A., Lutz, M., & Pradeep, V. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00267 · Cited by 34
“Glasner et al. [23] united the classical and example-based SR by exploiting the patch recurrence within and across image scales.”
BackgroundMethodAcross Scales and Across Dimensions: Temporal Super-Resolution Using Deep Internal Learning
Zuckerman, L. P., Naor, E., Pisha, G., Bagon, S., & Irani, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58571-6_4 · Cited by 33
Self-citationSuper-resolution of license plate images using attention modules and sub-pixel convolution layers
Nascimento, V., Laroca, R., Lambert, J. D. A., Schwartz, W. R., & Menotti, D. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.05.005 · Cited by 36
“Early SISR methods were generally classified into four categories: prediction models, edge-based methods, image statistical methods, and example-based methods [20]– [24].”
MethodInpainting by Joint Optimization of Linear Combinations of Exemplars
Wohlberg, B. E. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2095842 · Cited by 33
“The final result is highly dependent on fill order, and while significant progress has been made on the choice of this order, the greedy nature of such a process leads to artifacts in some cases.”
BackgroundFRESH—FRI-Based Single-Image Super-Resolution Algorithm
Wei, X., & Dragotti, P. L. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2563178 · Cited by 33
“Contrary to [17] and [19], we use self-learning algorithms only to refine our FRI based method.”
MethodImage Deblurring and Super-Resolution Using Deep Convolutional Neural Networks
Albluwi, F., Krylov, V. A., & Dahyot, R. (2018) · Machine learning for signal processing ... · doi:10.1109/mlsp.2018.8516983 · Cited by 41
“The example-based methods are divided into two kinds: internal methods [4, 5, 6] and external example-based methods [7, 8, 9, 10, 11, 12].”
MethodDictionary Learning for Deblurring and Digital ZoomPreprint
Couzinié-Devy, F., Mairal, J., Bach, F., & Ponce, J. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1110.0957 · Cited by 37
“In textured areas, we perform as good as [12].”
InfluentialAdvances and Future Prospects in Building Extraction From High-Resolution Remote Sensing Images
Yang, D., Gao, X., Yang, Y., Guo, K., Han, K., & Xu, L. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3538662 · Cited by 39
“These methods enhance image resolution to address the lack of feature details in low-and medium-resolution images [132].”
Transform a Simple Sketch to a Chinese Painting by a Multiscale Deep Neural Network
Lin, D., Wang, Y., Xu, G., Li, J., & Fu, K. (2018) · Algorithms · doi:10.3390/a11010004 · Cited by 32
Ren, C., He, X., Pu, Y., & Nguyen, T. Q. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2902794 · Cited by 33
Li, Y., Ma, C., Zhang, T., Li, J., Ge, Z., Li, Y., & Serikawa, S. (2019) · IEEE Access · doi:10.1109/access.2019.2925209 · Cited by 33
“Glasner et al. [13] proposed the anchoring field regression (anchored neighborhood regression, A + ) method to study a sparse dictionary and return a fixed number of fast superreso-lution dictionary atoms.”
MethodBlind single image super-resolution with a mixture of deep networks
Wang, Y., Wang, L., Wang, H., Li, P., & Lu, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107169 · Cited by 32
DynaVSR: Dynamic Adaptive Blind Video Super-Resolution
Lee, S., Choi, M., & Lee, K. M. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00214 · Cited by 38
Point-based rendering enhancement via deep learning
Bui, G. T. T., Le, T., Morago, B., & Duan, Y. (2018) · The Visual Computer · doi:10.1007/s00371-018-1550-6 · Cited by 38
“Glasner et al. [11] proposed a method to combine example-based SR constraints and classical SR constraints in a unified framework which allows for inter-patch search.”
MethodA Survey on Intelligent Solutions for Increased Video Delivery Quality in Cloud–Edge–End Networks
Shi, W., Li, Q., Qian, Y., Wang, F., Shen, G., Jiang, Y., Xu, Y., Ma, L., & Muntean, G. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3427360 · Cited by 39
“Typically, video content is transmitted from a cloud server to end users, possibly undergoing acceleration at the edge.”
Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution
Li, X. R., Liu, J., Chen, Z., Zou, Y., Ma, L., Fan, X., & Liu, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72646-0_16 · Cited by 76
Nonlinear neighbor embedding for single image super-resolution via kernel mapping
Chen, X., & Qi, C. (2013) · Signal Processing · doi:10.1016/j.sigpro.2013.06.016 · Cited by 31
“Instead of relying on an external training set, several recently proposed SR approaches [19,20] exploit the information of the input LR image itself to serve as the training set.”
MethodExample-Based Super-Resolution via Structure Analysis of Patches
Kim, C., Choi, K., & Ra, J. B. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2249514 · Cited by 31
“[8] combined reconstruction-based and example-based SR algorithms.”
Con-Patch: When a Patch Meets Its Context
Romano, Y., & Elad, M. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2576402 · Cited by 31
SRHRF+: Self-Example Enhanced Single Image Super-Resolution Using Hierarchical Random Forests
Huang, J., Liu, T., Dragotti, P. L., & Stathaki, T. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.144 · Cited by 33
“The advantage of these self-example based approaches [7, 6, 1, 8, 19, 24, 22] is that they exploit repetitive structure and can adapt to the characteristics of the input image.”
BackgroundMethodInfluentialEfficient Module Based Single Image Super Resolution for Multiple Problems
Park, D., Kim, K., & Chun, S. Y. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00133 · Cited by 32
“An example based SR method was proposed based on Bayesian belief propagation [6] and a patch based SR method was proposed by combining a conventional multiple image based SR and an example based SR [7].”
MethodSuper-resolved thermal imagery for high-accuracy facial areas detection and analysis
Kwaśniewska, A., Rumiński, J., Szankin, M., & Kaczmarek, M. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.103263 · Cited by 32
Coronary Magnetic Resonance Angiography in Chronic Coronary Syndromes
Hajhosseiny, R., Muñoz, C., da Cruz, G. J. L., Khamis, R., Kim, W. Y., Prieto, C., & Botnar, R. M. (2021) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2021.682924 · Cited by 32
Modeling deformable gradient compositions for single-image super-resolution
Zhu, Y., Zhang, Y., Bonev, B., & Yuille, A. (2015) · 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.2015.7299180 · Cited by 36
“Cui et al. [4] follow the gradual upscaling strategy from [8] [11] and apply the Collaborative Local Auto-encoder (CLA) to introduce the information of the external data in each step.”
InfluentialSingle-Image Superresolution of Natural Stochastic Textures Based on Fractional Brownian Motion
Zachevsky, I., & Zeevi, Y. Y. J. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2312284 · Cited by 31
“A comparison of the performance of the proposed algorithm with that of a state-of-the-art method, based on selfsimilarity [1], is shown in Fig.”
BackgroundMethodInfluentialEnsemble Super-Resolution With a Reference Dataset
Jiang, J., Yu, Y., Wang, Z., Tang, S., Hu, R., & Ma, J. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2890149 · Cited by 33
“The prior knowledge, such as piecewise smoothness [5]–[7], shape edges [8], [9], textures [10], local/nonlocal similar patterns [11]–[14], lowrank constraint [15], [16], and sparse representations under certain transformations [17]–[21], have been investigated to regularize the SR reconstruction procedures.”
BackgroundZhao, J., Chen, C., Zhou, Z., & Cao, F. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.12.036 · Cited by 31
Temporal Super Resolution from a Single Quasi-periodic Image Sequence Based on Phase Registration
Makihara, Y., Mori, A., & Yagi, Y. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19315-6_9 · Cited by 30
“[8] proposed a sophisticated framework, combining the two approaches by using the patch recurrence within and across scales of a single image.”
MethodSingle-image super-resolution using multihypothesis prediction
Chen, C., & Fowler, J. E. (2012) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2012.6489079 · Cited by 30
“[9] combined both the classical multi-image and example-based SR techniques and exploited patch redundancy within as well as across scales to reconstruct the unknown HR image.”
BackgroundSparsity-Based Super Resolution for SEM Images
Tsiper, S., Dicker, O., Kaizerman, I., Zohar, Z., Segev, M., & Eldar, Y. C. (2017) · Nano Letters · doi:10.1021/acs.nanolett.7b02091 · Cited by 30
“Among these are approaches that incorporate deep neural networks [43], internal patch recurrence [44, 45], super-resolution forests [46, 47], and more, that were shown to produce successful results for natural images.”
BackgroundUnsupervised Image-to-Image Translation with Self-Attention Networks
Kang, T., & Lee, K. H. (2020) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp48618.2020.00-92 · Cited by 36
“can enable both the generator and discriminator to efficiently model relationships between widely separated spatial regions. non-local mechanisms also have become a important part of image generation [4, 9, 5, 6, 12, 3]. In the self attention module (Figure 1.), image features from the previous hidden layer xare firstly…”
BackgroundA spatial finer electric load estimation method based on night-light satellite image
Li, P., Peiran, L., Zhang, H., Wang, *., Song, X., & Shibasaki, R. (2020) · Energy · doi:10.1016/j.energy.2020.118475 · Cited by 30
Improved dual-scale residual network for image super-resolution
Liu, H., & Cao, F. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.08.008 · Cited by 32
Deep Residual Dual-Attention Network for Super-Resolution Reconstruction of Remote Sensing Images
Huang, B., He, B., Wu, L., & Guo, Z. (2021) · Remote Sensing · doi:10.3390/rs13142784 · Cited by 30
“Considering the high research cost and long hardware iteration development cycle required to physically improve imaging sensors, it is increasingly important to improve the algorithms used for super-resolution (SR) reconstruction [1] of remote sensing images.”
BackgroundZhu, F., Wang, C., Zhu, B., Sun, C., & Qi, C. (2023) · The Egyptian Journal of Remote Sensing and Space Science · doi:10.1016/j.ejrs.2022.12.008 · Cited by 37
Simple, Accurate, and Robust Nonparametric Blind Super-Resolution
Shao, W., & Elad, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-21969-1_29 · Cited by 30
“As for single image non-blind SR, we mention few commonly used options: bicubic low-pass filter (implemented by Matlab’s default function imresize) [8-13, 21, 34, 35], 7×7 Gaussian kernel with δ 1.”
MethodPan, J., Xu, B., Bai, H., Tang, J., & Yang, M. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243059 · Cited by 33
“Exploring these similar contents would help image restoration as demonstrated by several variational model-based methods [22], [40], [41], [42].”
MethodSingle image super-resolution using regularization of non-local steering kernel regression
Zhang, K., Gao, X., Li, J., & Xia, H. (2015) · Signal Processing · doi:10.1016/j.sigpro.2015.11.025 · Cited by 29
Yang, Q., Zhang, Y., Zhao, T., & Chen, Y. (2017) · ISA Transactions · doi:10.1016/j.isatra.2017.03.001 · Cited by 32
“Article [15] however proposes a framework to combine the power of classical SR and example-based SR.”
BackgroundMethodInfluentialWang, H., Gao, X., Zhang, K., & Li, J. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2700725 · Cited by 29
Zhang, N., Wang, Y., Zhang, X., Xu, D., & Wang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2972300 · Cited by 30
“Various methods such as [53]–[55] [56], use LR images for training and can be regarded as hybrids of reconstruction-based and learning-based methods.”
MethodRemote sensing image recovery via enhanced residual learning and dual-luminance scheme
Ren, C., He, X., Qing, L., Wu, Y., & Pu, Y. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107013 · Cited by 30
Iwamoto, Y., Takeda, K., Li, Y., Shiino, A., & Chen, Y. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3215137 · Cited by 31
A Deep Learning Based No-Reference Image Quality Assessment Model for Single-Image Super-Resolution
Bare, B., Li, K., Yan, B., Feng, B., & Yao, C. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461931 · Cited by 32
“These 9 different methods are : bicubic interpolation (Bicubic), back projection (BP) [20], Shan08 [12], Glasner09 [13], Yang10 [14], Dong11 [15], Yang13 [16], Timofte13 [17], and SRCNN [18].”
MethodLight Field Super-Resolution: A Benchmark
Cheng, Z., Xiong, Z., Chen, C., & Liu, D. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00231 · Cited by 29
“Natural image priors such as edge structure and patch recurrence are widely used for single image SR in an early stage [18, 57].”
BackgroundA DEM Super-Resolution Reconstruction Network Combining Internal and External Learning
Lin, X., Zhang, Q., Wang, H., Yao, C., Chen, C., Cheng, L., & Li, Z. (2022) · Remote Sensing · doi:10.3390/rs14092181 · Cited by 30
“, are within the low ‐ resolution DEM, can be seen as multiple constraints of the low ‐ resolution DEM on the high ‐ resolution DEM [27].”
Sajjad, M., Mehmood, I., & Baik, S. W. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2014.10.012 · Cited by 29
“For this purpose, all reference images provided by [56,57,64] were guaranteed to be distortion free.”
MethodCT-SRCNN: Cascade Trained and Trimmed Deep Convolutional Neural Networks for Image Super Resolution
Ren, H., El‐Khamy, M., & Lee, J. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00160 · Cited by 31
E-DBPN: Enhanced Deep Back-Projection Networks for Remote Sensing Scene Image Superresolution
Yu, Y., Li, X., & Fu-xian, L. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2966669 · Cited by 28
Toward image super-resolution based on local regression and nonlocal means
Bastanfard, A., Amirkhani, D., & Mohammadi, M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12584-x · Cited by 28
“[17], which did not require any model data.”
Background
Metadata
- Authors
- Glasner, D., Bagon, S., & Irani, M.
- Affiliations
- Weizmann Institute of Science (IL)
- ORCID
- Bagon, Shai
- Venue
- 2009 IEEE 12th International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2009-09
- Pages
- 349-356
- OpenAlex
- W2534320940
- Cited by
- 1,889
- References
- 20
- Citations by year
- 2026: 15 · 2025: 49 · 2024: 94 · 2023: 113 · 2022: 109 · 2021: 153 · 2020: 162 · 2019: 154 · 2018: 176 · 2017: 154 · 2016: 154 · 2015: 143 · 2014: 139 · 2013: 103 · 2012: 73
- FWCI
- 46.55
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Keywords
- single image super-resolution, multi-frame super-resolution, example-based super-resolution
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.