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 601–700 of 1,002
Fast multi-channel image reconstruction using a novel two-dimensional algorithm
Bin, S. Q., & Xia, Y. S. (2013) · Multimedia Tools and Applications · doi:10.1007/s11042-013-1371-6 · Cited by 20
“[7].”
High quality image reconstruction from RAW and JPEG image pair
Yuan, L., & Sun, J. Z. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126492 · Cited by 20
“(1) The first term Er(R h;Rl) enforces the reconstruction constraint.”
BackgroundSingle image super-resolution using iterative Wiener filter
Hung, K.-W., & Siu, W.-C. (2012) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2012.6288120 · Cited by 20
“Index Terms—Iterative Wiener filter, super-resolution”
Non‐local feature back‐projection for image super‐resolution
Zhang, X., Liu, Q., Li, X., Zhou, Y., & Zhang, C. (2016) · IET Image Processing · doi:10.1049/iet-ipr.2015.0467 · Cited by 20
Low-rank sparse representation for single image super-resolution via self-similarity learning
Shi, J., & Qi, C. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532593 · Cited by 20
“[1] first combined the self-similarity learning with example learning-based SR.”
BackgroundMultiple-image super-resolution on mobile devices: an image warping approach
Gallego, N. P. D., & Ilao, J. P. (2017) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-016-0156-z · Cited by 20
Automatic Classification of Low-Resolution Chromosomal Images
Swati, S., Sharma, M., & Vig, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11024-6_21 · Cited by 23
“Existing super-resolution (SR) algorithms are grouped into four groups: image statistical methods [19], example-based methods [37], [16], [11], [30], [10], [15], [35], [18], prediction models [20] and edge-based methods [14], [34].”
BackgroundSuper-resolution Quality Criterion (SRQC): a super-resolution image quality assessment metric
Greeshma, M. S., & Bindu, V. R. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09352-0 · Cited by 25
“5, we demonstrate the f ψ of SR image generated through four SR algorithms such as Bicubic, Glasner [8], Yang [46], and SRCNN [2].”
MethodMoESR: Blind Super-Resolution using Kernel-Aware Mixture of Experts
Emad, M., Peemen, M., & Corporaal, H. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00406 · Cited by 31
Unfolded Deep Kernel Estimation for Blind Image Super-Resolution
Zheng, H., Yong, H., & Zhang, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19797-0_29 · Cited by 25
Digital restoration of damaged mural images
Purkait, P., & Chanda, B. (2012) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/2425333.2425382 · Cited by 20
“Recent studies on single frame Super Resolution [12], [15] suggest that patches in a natural image tend to redundantly recur many times inside the same image, both within the same scale, as well as across different scales.”
BackgroundImage Super‐Resolution Based on Sparse Representation via Direction and Edge Dictionaries
Zhu, X., Wang, X., Wang, J., Jin, P., Liu, L., & Mei, D. (2017) · Mathematical Problems in Engineering · doi:10.1155/2017/3259357 · Cited by 20
“According to the processing method, it mainly includes three kinds of SR approaches: interpolation-based methods [3], reconstruction-basedmethods [4], and learning-basedmethods [5].”
MethodNoise robust single image super-resolution using a multiscale image pyramid
Hu, J., Wu, X., & Zhou, J. (2018) · Signal Processing · doi:10.1016/j.sigpro.2018.02.020 · Cited by 20
Fast deep parallel residual network for accurate super resolution image processing
Sha, F., Zandavi, S. M., & Chung, Y. Y. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.03.032 · Cited by 21
Frequency Separation Network for Image Super-Resolution
Li, S., Cai, Q., Li, H., Cao, J., Wang, L., & Li, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2972927 · Cited by 20
“The representative linear interpolation and bicubic interpolation [5], [6], [17], [18] can upsample image very fast, but cannot reconstruct detailed and realistic textures.”
BackgroundSparse representation with morphologic regularizations for single image super-resolution
Liu, W., & Shutao Li, A. (2013) · Signal Processing · doi:10.1016/j.sigpro.2013.11.032 · Cited by 19
Optimized neighbor embeddings for single-image super-resolution
Türkan, M., Thoreau, D., & Guillotel, P. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738133 · Cited by 19
“A unified framework combining the classical multi-image and exemplar-based methods has been proposed in [9] by considering SR from a single LR image.”
BackgroundMethodDeep-Learning-Based Computer-Aided Systems for Breast Cancer Imaging: A Critical Review
Jiménez-Gaona, Y., Rodríguez-Álvarez, M. J., & Lakshminarayanan, V. (2020) · Applied Sciences · doi:10.3390/app10228298 · Cited by 123
A unifying resolution-independent formulation for early vision
Viola, F., Fitzgibbon, A. W., & Cipolla, R. (2012) · 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.2012.6247713 · Cited by 19
“It is a strength of our model that enormous upsampling ratios can be obtained easily, while some example-based methods [7] require repeated application of the pixel-based method, with a loss in quality.”
MethodSelf-learning-based single image super-resolution of a highly compressed image
Kang, L., Chuang, B.-C., Hsu, C., Lin, C., & Yeh, C. (2013) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2013.6659292 · Cited by 20
Image Super-Resolution via Local Self-Learning Manifold Approximation
Dang, C., Aghagolzadeh, M., & Radha, H. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2332118 · Cited by 19
“Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org.”
BackgroundMethodVishnukumar, S., & Wilscy, M. (2017) · Optics Communications · doi:10.1016/j.optcom.2017.05.074 · Cited by 19
A fast single-image super-resolution method implemented with CUDA
Yuan, Y., Yang, X., Wu, W., Hu, L., Liu, Y., & Liu, K. (2018) · Journal of Real-Time Image Processing · doi:10.1007/s11554-018-0774-z · Cited by 19
Heavy-Tailed Self-Similarity Modeling for Single Image Super Resolution
Chantas, G., Nikolopoulos, S., & Kompatsiaris, I. Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3038521 · Cited by 19
“Another related work is that of Glasner et al. [29], where example-based constraints are combined with the assumption of the imaging model of (1).”
BackgroundSingular value decomposition based fusion for super-resolution image reconstruction
Nasir, H., Stanković, V., & Marshall, S. (2011) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2011.6144138 · Cited by 19
A fast deconvolution-based approach for single-image super-resolution with GPU acceleration
Jung, C., Peng, K., Sun, Z., & Gu, A. (2015) · Journal of Real-Time Image Processing · doi:10.1007/s11554-015-0513-7 · Cited by 20
“Example-based SR approaches [3, 4, 6] assume that the high-frequency details lost in the LR image can be effectively predicted from a set of LR and HR training image pairs.”
BackgroundSRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial NetworksPreprint
Guan, J., Pan, C., Li, S., & Yu, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11821 · Cited by 19
“Some example-based approaches used image self-similarity property to reduce the amount of training data needed [12, 10, 11], and increased the size of the limited internal dictionary [17].”
Single-image super-resolution using iterative Wiener filter based on nonlocal means
Hung, K.-W., & Siu, W.-C. (2015) · Signal Processing Image Communication · doi:10.1016/j.image.2015.07.003 · Cited by 18
Superresolution from a Single Noisy Image by the Median Filter Transform
López‐Rubio, E. (2016) · SIAM Journal on Imaging Sciences · doi:10.1137/15m1020459 · Cited by 18
“To this end, we have considered three images from the Weizmann Institute of Science [20] which accompany the method proposed in [19].”
MethodSuperresolution of MRI brain images using unbalanced 3D Dense-U-Net network
Kolařík, M., Bürget, R., Uher, V., & Povoda, L. (2019) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp.2019.8768829 · Cited by 18
“Notable works from era before the deep learning algorithms became widely used are example based algorithms [3] and single image superresolution [4].”
BackgroundRZSR: Reference-Based Zero-Shot Super-Resolution With Depth Guided Self-Exemplars
Yoo, J.-S., Kim, D.-W., Lu, Y., & Jung, S. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3202018 · Cited by 21
“In cross-scale patch matching [28], the best match for LR son is found from I↓4.”
BackgroundMethodInfluentialSingle image super resolution with high resolution dictionary
Mu, G., Gao, X., Zhang, K., Li, X., & Tao, D. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6115630 · Cited by 18
“In our experiments, 3X magnification are conducted to compare with several state-of-art methods: Sparse coding (SC) (we set overlap = 2 to achieve the best results) [4], Kernel ridge regression (KRR) [5] and Glasner algorithm [6].”
MethodSuper-Resolution Land Cover Mapping Using Multiscale Self-Similarity Redundancy
Zhang, Y., Ling, F., Li, X., & Du, Y. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2480120 · Cited by 18
“This is due to the fact that small sized fraction image patches contain simple spatial patterns, which has a great probability to recur itself in its down-sampled version [35].”
BackgroundMethodInfluentialRobust All-in-focus Super-Resolution for Focal Stack Photography
Lee, M., & Tai, Y. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2523419 · Cited by 18
“By using multiple images in deconvolution, our method is robust to image noise as well as small errors in defocus kernels estimation.”
MethodLocal patch encoding-based method for single image super-resolution
Zhao, Y. S., Wang, R., Jia, W., Yang, J., Wang, W., & Gao, W. (2017) · Information Sciences · doi:10.1016/j.ins.2017.12.032 · Cited by 20
Self-Learning Super-Resolution Using Convolutional Principal Component Analysis and Random Matching
Xu, J., Li, M., Fan, J., Zhao, X., & Chang, Z. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2871948 · Cited by 18
“WE COMPARE THE PROPOSED ALGORITHM WITH BI-CUBIC [60] INTERPOLATION, LAPSRN ALGORITHM [15], A+ ALGORITHM [23], GLASNER’S ALGORITHM [43], CONVOLUTION NEURAL NETWORKS(SR- CNN) [7] ALGORITHM CCR ALGORITHM [61], VDSR ALGORITHM [5] AND JIA-BIN HUANG’S ALGORITHM [36].”
BackgroundMethodInfluentialGibbs-ringing artifact suppression with knowledge transfer from natural images to MR images
Zhao, X., Zhang, H., Zhou, Y., Bian, W., Zhang, T., & Zou, X. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08143-6 · Cited by 18
“We construct an end-to-end model based on the EDSR model [35], which was originally designed for single (natural) image super-resolution (SISR).”
BackgroundRestore from Restored: Video Restoration with Pseudo Clean Video
Lee, S., Cho, D., Kim, J., & Kim, T. H. (2021) · 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/cvpr46437.2021.00354 · Cited by 27
“es used for image restoration is patchrecurrence that similar patches are existing across dierent image scales. In particular, it has been adopted a lot in single image super-resolution (SR) methods [10,12,13]. In a video, not only similar but exactly the same patches can exist in dierent multiple video frames. Althou…”
BackgroundSatellite image super-resolution based on progressive residual deep neural network
Zhang, J., Liu, S., Peng, Y., & Li, J. (2020) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.14.032610 · Cited by 18
Sander, J., de Vos, B. D., & Išgum, I. (2021) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.2580412 · Cited by 21
“Thereafter, latent representations zn and zn+1 are combined using a convex combination zα(zn,zn+1) = (1 − α)zn + αzn+1 for α ∈ [0, 1].”
MethodHigh-Level Task-Driven Single Image Deraining: Segmentation in Rainy Days
Guo, M., Chen, M., Ma, C., Li, Y., Li, X., & Xie, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63830-6_30 · Cited by 18
Pre‐training of gated convolution neural network for remote sensing image super‐resolution
Peng, Y., Wang, X., Zhang, J., & Liu, S. (2021) · IET Image Processing · doi:10.1049/ipr2.12096 · Cited by 18
“And compared with the traditional algorithm, deep convolution neural networks show an overwhelming advantage to deal with super-resolution (SR) problems [5, 6].”
BackgroundSingle image super-resolution using feature adaptive learning and global structure sparsity
Liu, J., Liu, Y., Wu, H., Wang, J., Li, X., & Zhang, C. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.108184 · Cited by 18
Pseudo 3D Auto-Correlation Network for Real Image Denoising
Hu, X., Ma, R., Liu, Z., Cai, Y., Zhao, X., Zhang, Y., & Wang, H. (2021) · 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/cvpr46437.2021.01591 · Cited by 33
“The self-similar prior provides a powerful self-prediction ability for natural image restoration [5, 18, 58].”
BackgroundVideo Temporal Super-Resolution Based on Self-similarity
Shimano, M., Okabe, T., Sato, I., & Sato, Y. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19315-6_8 · Cited by 20
“[5] reported, 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.”
BackgroundInfluentialBrief Survey of Single Image Super-Resolution Reconstruction Based on Deep Learning Approaches
Wang, W., Hu, Y., Luo, Y., & Zhang, T. (2020) · Sensing and Imaging · doi:10.1007/s11220-020-00285-4 · Cited by 22
On Constructing $z$ -Dimensional DIBR-Synthesized Images
Mao, Y. L., Cheung, G., & Ji, Y. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2573142 · Cited by 17
“1The goal of SR “is to recover a high resolution image from one or more low resolution input images” [29].”
BackgroundA convolutional neural network with sparse representation
Yang, Y., Yang, J., Lu, Z., & Liu, D. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106419 · Cited by 17
Test-Time Adaptation for Video Frame Interpolation via Meta-Learning
Choi, M., Choi, J., Baik, S., Kim, T. H., & Lee, K. M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3129819 · Cited by 21
“Examples include single-image super-resolution approaches exploiting self-similarities inherent in the target image [13], [14], [15], [16], [17], [18],”
BackgroundLightweight Image Super-Resolution With Pyramid Clustering Transformer
Li, M., Ma, B., & Zhang, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3296526 · Cited by 23
“However, the multi-scale self-similarity [45], [46], [47] has not been explored in a complete SA calculation of Transformer.”
Affine Non-local Means Image Denoising
Anand, R., Koti, V. M., Sharma, M., Ajagekar, S. S., Dhabliya, D., & Gupta, A. (2023) · Smart innovation, systems and technologies · doi:10.1007/978-981-99-6702-5_45 · Cited by 17
Toward DNN of LUTs: Learning Efficient Image Restoration With Multiple Look-Up Tables
Li, J., Chen, C., Cheng, Z., & Xiong, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3401048 · Cited by 17
“Example-based methods leverage a dataset of LR-HR image patch pairs [27], [28], [29], [30], or exploit self-similarity inside the LR image [31], among which sparse coding methods learn a compact representation of the patches, showing promising results [32], [33].”
MethodLearning context-aware sparse representation for single image super-resolution
Yang, M.-C., Wang, C., Hu, T.-Y., & Wang, Y.-C. F. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6115687 · Cited by 17
“To compare our approach with other existing interpolation or learning-based SR methods, we consider bicubic interpolation, locally linear embedding (LLE) for SR [7], sparse representation for SR [9], our previous SVR-based approach [10], and the approach of Irani et al. [13].”
BackgroundMethodInfluentialEdge Curve Scaling and Smoothing with Cubic Spline Interpolation for Image Up-Scaling
Wu, W.-C., Wang, T.-H., & Chiu, C. (2014) · Journal of Signal Processing Systems · doi:10.1007/s11265-014-0936-6 · Cited by 17
“[18] propose a multi-scale example super resolution using a single image.”
BackgroundTemporally Coherent Superresolution of Textured Video via Dynamic Texture Synthesis
Hsu, C., Kang, L., & Lin, C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2387416 · Cited by 17
MobiUP: An Upsampling-Based System Architecture for High-Quality Video Streaming on Mobile Devices
Shuai, H.-H., Yang, D.-N., Cheng, W.-H., & Chen⋆, M.-S. (2011) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2011.2156910 · Cited by 17
“coherence as a mask, and then apply SR [17] on these masking regions to obtain the required high-resolution version for all regions of interest.”
BackgroundMethodInfluentialSingle image super-resolution using dictionary-based local regression
Ram, S., & Rodrı́guez, J. J. (2014) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2014.6806044 · Cited by 17
“…been developed using the fact that images possess a large number of self-similarities, I.e., local image structures tend to reappear within and across different image scales [3], [5], [18], and thus the image SR problem can be regularized based on these examples rather than some external database.”
BackgroundContext-aware joint dictionary learning for color image demosaicking
Hua, K., Hidayati, S. C., He, F.-L., Wei, C.-P., & Wang, Y.-C. F. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.03.004 · Cited by 17
Super-Resolution of VIIRS-Measured Ocean Color Products Using Deep Convolutional Neural Network
Liu, X., & Wang, M. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2992912 · Cited by 17
Kim, K., & Lee, Y. (2021) · Nuclear Engineering and Technology · doi:10.1016/j.net.2021.01.011 · Cited by 17
Zero-Shot Super-Resolution With a Physically-Motivated Downsampling Kernel for Endomicroscopy
Szczotka, A. B., Shakir, D. I., Clarkson, M. J., Pereira, S. P., & Vercauteren, T. K. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3067512 · Cited by 17
“It was shown that natural images contain recurring patches that capture the image representation well, so they may contribute to improving image content through the use of SR approaches [15].”
U-Shaped Attention Connection Network for Remote-Sensing Image Super-Resolution
Jiang, W., Zhao, L., Wang, Y., Liu, W., & Liu, B. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3127988 · Cited by 17
Scale-Arbitrary Invertible Image Downscaling
Xing, J., Hu, W., Xia, M., & Wong, T. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3296891 · Cited by 30
“But the lost information during the downscaling process makes the SR problem highly ill-posed [Dong et al. 2015; Glasner et al. 2009; Yang et al. 2010].”
BackgroundSpace–time super-resolution with patch group cuts prior
Li, T., He, X., Teng, Q., Wang, Z., & Ren, C. (2014) · Signal Processing Image Communication · doi:10.1016/j.image.2014.10.007 · Cited by 18
Image super-resolution using non-local Gaussian process regression
Wang, H., Gao, X., Zhang, K., & Li, J. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.01.073 · Cited by 17
Single image super resolution using neighbor embedding and statistical prediction model
Rahiman, V. A., & George, S. N. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2016.12.018 · Cited by 17
Liang, M., Du, J., Li, L., Xue, Z., Wang, X., Kou, F., & Wang, X. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3034261 · Cited by 23
Expectation-Maximization Attention Cross Residual Network for Single Image Super-resolution
Du, X., Niu, J., & Liu, C. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00099 · Cited by 16
“The improved work such as [10], [9] uses the prior self-similarity that clear image patches in natural images.”
BackgroundDing, H., Li, F., Chen, X., Ma, J., Nie, S., Ye, R., & Yuan, C. (2022) · Cells · doi:10.3390/cells11152394 · Cited by 16
“To compare the performance of the modification, we trained the CycleGAN (U‐Net as the generator) and S‐Transformer (Swin‐Trans‐ former as the generator) with the same training dataset.”
BackgroundMethodInfluentialVirtual Super Resolution of Scale Invariant Textured Images Using Multifractal Stochastic Processes
Chainais, P., Koenig, E., Delouille, V., & Hochedez, J. ‐. (2010) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-010-0222-6 · Cited by 19
Single image super-resolution via subspace projection and neighbor embedding
Li, X., He, H., Yin, Z., Chen, F., & Cheng, J. S. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.02.026 · Cited by 16
“Generally speaking, those methods can be separated into three categories: interpolation-based [3,4], multi-frame-based [5–7], and learning-based [8].”
MethodFinding and improving the key-frames of long video sequences for face recognition
Nasrollahi, K., & Moeslund, T. B. (2010) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2010.5634491 · Cited by 16
Learning From Errors in Super-Resolution
Tang, Y., & Yuan, Y. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2301732 · Cited by 16
Super Resolution from a Single Image Based on Self Similarity
Chen, S., Gong, H., & Li, C. (2011) · International Conference on Computational and Information Sciences · doi:10.1109/iccis.2011.268 · Cited by 16
“Self-similarity has been proposed in several researches ([4, 5]).”
BackgroundMethodPatch-based spatio-temporal super-resolution for video with non-rigid motion
Salvador, J., Kochale, A., & Schweidler, S. (2013) · Signal Processing Image Communication · doi:10.1016/j.image.2013.02.002 · Cited by 16
Single image super-resolution using locally adaptive multiple linear regression
Yu, S., Kang, W., Ko, S., & Paik, J. (2015) · Journal of the Optical Society of America A · doi:10.1364/josaa.32.002264 · Cited by 16
“proposed a more efficient way to find patches using the redundancy between in- and cross-scaled images in the scale space [8].”
BackgroundMethodDeep learning based image super-resolution with coupled backpropagation
Guo, T., Mousavi, H. S., & Monga, V. (2016) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2016.7905839 · Cited by 18
“Some methods explore the similarity of self-examples as [5–9], while other methods map the LR to HR patches with use of external samples, as [10–17].”
MethodImage super-resolution via deep dilated convolutional networks
Huang, Z., Wang, L., Meng, G., & Pan, C. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296422 · Cited by 16
Sparse representation and adaptive mixed samples regression for single image super-resolution
Zhang, C., Liu, W., Liu, J., Liu, C., & Shi, C. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.06.001 · Cited by 16
Depth image super-resolution based on joint sparse coding
Li, B., Zhou, Y., Zhang, Y., & Wang, A. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.07.023 · Cited by 16
Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution
Tej, A. R., Halder, S. S., Shandeelya, A. P., & Pankajakshan, V. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207102 · Cited by 17
Deep Networks With Detail Enhancement for Infrared Image Super-Resolution
Yang, Y., Li, Q., Yang, C., Fu, Y., Feng, H., Xu, Z., & Chen, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3017819 · Cited by 18
“Given low-resolution (LR) infrared images, we focus on developing effective algorithms to restore details through solving an ill-posed inverse problem, which is essential to enable reliable target detection and recognition tasks but only available in high-resolution (HR) infrared images [2], [3].”
BackgroundDual-view Attention Networks for Single Image Super-Resolution
Guo, J., Ma, S., Zhang, J., Zhou, Q., & Guo, S. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413613 · Cited by 16
“Single Image super-resolution (SISR) is a hot topic in multimedia and computer vision [7, 9, 10, 22, 42].”
BackgroundGradient guided image interpolation
Jing, G., Choi, Y., Wang, J., & Wang, W. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025365 · Cited by 16
“, [6] [7] [8] [9] [10] [11] [12] [13] [14]).”
Single image super resolution via neighbor reconstruction
Zhang, Z., Chen, X., Zhang, Z., Guo, C., Cai, Y., Wang, Z., Li, H., & Hancock, E. R. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.04.021 · Cited by 16
Edge preserving single image super-resolution with improved visual quality
Vishnukumar, S., Nair, P. (. ). M. S., & Wilscy, M. (2014) · Signal Processing · doi:10.1016/j.sigpro.2014.05.033 · Cited by 15
Liu, X., Yang, Z., Wang, J., Liu, J., Zhang, K., & Hu, W. (2017) · Journal of medical imaging · doi:10.1117/1.jmi.4.1.014002 · Cited by 15
“(16) and (17), a clean image can be divided into foreground region and background region, and the grayscale value in each region tends to be uniform.”
BackgroundSrinivasan, K., & Kumaran, S. S. (2020) · Materials Today Proceedings · doi:10.1016/j.matpr.2020.03.347 · Cited by 17
Deep ResNet Based Remote Sensing Image Super-Resolution Reconstruction in Discrete Wavelet Domain
Qin, Q., Dou, J., & Tu, Z. (2020) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661820030232 · Cited by 15
“Stationary wavelet transform (SWT) [12] solves this problem of shift invariance.”
BackgroundSpatial Super Resolution of Real-World Aerial Images for Image-Based Plant Phenotyping
Aslahishahri, M., Stanley, K. G., Duddu, H., Shirtliffe, S. J., Vail, S. L., & Stavness, I. (2021) · Remote Sensing · doi:10.3390/rs13122308 · Cited by 19
“These patches are extracted from the self-similarity property of natural images [49], such that the smallest patches in a natural image are likely to be observed in the down-scaled version of the same image [50,51].”
BackgroundSeo, M., Jung, W., Jeong, G., Yang, S., Shin, I., Lee, J. Y., Ahn, K. J., Kim, B., & Jang, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-69750-4 · Cited by 15
Kang, W., Yu, S., Seo, D., Jeong, J., & Paik, J. (2015) · Sensors · doi:10.3390/s150922826 · Cited by 15
“More specifically, destriping and denoising methods in the proposed framework are improved versions of the wavelet-Fourier [32] and multiscale Super-resolution (SR) [33] methods, respectively.”
BackgroundMethodA Random Walk on Image Patches
Taylor, K. M., & Meyer, F. G. (2012) · SIAM Journal on Imaging Sciences · doi:10.1137/110839370 · Cited by 19
Detail enhancement of image super-resolution based on detail synthesis
Xiao, J., Liu, E., Zhao, L., Wang, Y.-F., & Jiang, W. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.11.001 · Cited by 15
“Freedman [27] and Daniel [30] have used a series of LR images at different scales by downsampling the original LR image.”
MethodSymmetrical Residual Connections for Single Image Super-Resolution
Li, X., Sun, Y., Yang, Y., & Miao, C. (2019) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3282445 · Cited by 15
“[6] and [7] exploited the self-similarity property and constructed LR-HR patch pairs based on the scale-space pyramid of the LR input image.”
Learned Multi-View Texture Super-Resolution
Richard, A., Cherabier, I., Oswald, M. R., Tsiminaki, V., Pollefeys, M., & Konrad Schindler, B. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00065 · Cited by 16
“…SR is to fill in HR image patterns by leveraging a prior derived either from similar patches in other parts of the input image (self-examplars) [14, 21], or from similar image patches from an existing image database [13], or – most commonly – from previously seen training data [25, 48, 53, 54].”
Single Pair Cross-Modality Super Resolution
Shacht, G., Danon, D., Fogel, S., & Cohen‐Or, D. (2021) · 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/cvpr46437.2021.00631 · Cited by 21
Ghost-Free Deep High-Dynamic-Range Imaging Using Focus Pixels for Complex Motion Scenes
Woo, S.-M., Ryu, J.-H., & Kim, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3077137 · Cited by 15
Learning A Cascaded Non-Local Residual Network for Super-resolving Blurry Images
Bai, H., Cheng, S., Tang, J., & Pan, J. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00031 · Cited by 18
“As the image super-resolution is a highly ill-posed problem, conventional methods [31, 5, 24] develop image priors to solve this problem, whose performance is limited due to their complex optimization problems.”
BackgroundPractical application of random forests for super-resolution imaging
Huang, J., & Siu, W.-C. (2015) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2015.7169108 · Cited by 15
“Among the learning-based methods, the examplebased methods [8-10] search similar patches from an external database [8], from the input LR image itself across different scales [9] or from the local self-similar examples [10]; the sparse representation model based methods [11-14] use two coupled over-completed dictionar…”
Method
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.