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
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
“Non-local matching is also the essence of successful texture synthesis [12], super-resolution [16], and inpainting [1] algorithms.”
BackgroundPerceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283
“They group super-resolution techniques into prediction-based methods (bilinear, bicubic, Lanczos, [24]), edge-based methods [25,26], statistical methods [27,28,29], patch-based methods [25,30,31,32,33,34,35,36], and sparse dictionary methods [37,38].”
MethodImage Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105
Enhanced Deep Residual Networks for Single Image Super-Resolution
Lim, B., Son, S., Kim, H., Nah, S., & Lee, K. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.151 · Cited by 7,736
“Some approaches utilize image self-similarities to avoid using external databases [8, 6, 29], and increase the size of the limited internal dictionary by geometric transformation of patches [10].”
MethodAccurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870
“Early methods include interpolation such as bicubic interpolation and Lanczos resampling [7] more powerful methods utilizing statistical image priors [20, 13] or internal patch recurrence [9].”
BackgroundMethodShi, W., Caballero, J., Huszar, F., Totz, J., Aitken, A. P., Bishop, R., Rueckert, D., & Wang, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.207 · Cited by 7,570
“The goal of SISR methods is to recover a HR image from a single LR input image [14].”
MethodLearning a Deep Convolutional Network for Image Super-Resolution
Dong, C., Loy, C. C., He, K., & Tang, X. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_13 · Cited by 5,494
“These methods either exploit internal similarities of the same image [7,10,23], or learn mapping functions from external low- and high-resolution exemplar pairs [2,4,9,13,20,24,25,26,28].”
NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study
Agustsson, E., & Timofte, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.150 · Cited by 4,295
“Single image super-resolution as well as image restoration research literature spans over decades [36, 20, 4, 13, 16, 3, 15, 14, 6, 32, 54, 30, 17, 23, 12, 47, 48, 10, 21].”
BackgroundSingle image super-resolution from transformed self-exemplars
Huang, J.-B., Singh, A., & Ahuja, N. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299156 · Cited by 3,472
“To avoid using external databases and their associated problems, several approaches exploit internal patch redundancy for SR [10] [15] [13] [28].”
BackgroundMethodResultInfluentialOn Single Image Scale-Up Using Sparse-Representations
Zeyde, R., Elad, M., & Protter, M. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-27413-8_47 · Cited by 3,352
“4 Back-projection We may use back-projection method as suggested in [1] and implemented in [9].”
BackgroundMethodResultInfluentialLow-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding
Bevilacqua, M., Roumy, A., Guillemot, C., & Morel, M.-L. A. (2012) · Procedings of the British Machine Vision Conference 2012 · doi:10.5244/c.26.135 · Cited by 2,701
“The other approach is Neighbor Embedding (NE) [1, 2, 5], that first learns the local neighborhood of a LR patch and assumes that this is the best estimate for the local neighborhood of the corresponding HR patch.”
BackgroundDeeply-Recursive Convolutional Network for Image Super-Resolution
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.181 · Cited by 3,025
“Some of the more powerful methods utilize statistical image priors [27, 12] or internal patch recurrence [8, 10].”
MethodDeep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
Lai, W.-S., Huang, J.-B., Ahuja, N., & Yang, M.-H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.618 · Cited by 2,976
“Several methods [9, 12] exploit the self-similarity property in natural images and construct LR-HR patch pairs based on the scale-space pyramid of the low-resolution input image.”
MethodImage Super-Resolution via Deep Recursive Residual Network
Tai, Y., Yang, J., & Liu, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.298 · Cited by 2,415
“posed inverse problem of Super Resolution (SR), and have demonstrated superiority over reconstruction-based methods [4, 35] or other learning paradigms [20, 22, 23, 31].”
MethodDeep Learning for Image Super-Resolution: A Survey
Wang, Z., Chen, J., & Hoi, S. C. H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2982166 · Cited by 1,969
Lempitsky, V., Vedaldi, A., & Ulyanov, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00984 · Cited by 1,916
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Wang, X., Xie, L., Dong, C., & Shan, Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00217 · Cited by 1,684
“Single image super-resolution (SR) [13, 10, 27] is an active research topic, which aims at reconstructing a high-resolution (HR) image from its low-resolution (LR) counterpart.”
BackgroundUlyanov, D., Vedaldi, A., & Lempitsky, V. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01303-4 · Cited by 719
“te PSNRs using center crops of the generated images (tables1and2). While our method is still outperformed by learning-based approaches, it does considerably better than the non-trained ones (bicubic, [19], [27]). Visually, it seems to close most of the gap between non-trained methods and state-of-the-art trained ConvN…”
MethodNonlocally Centralized Sparse Representation for Image Restoration
Dong, W., Zhang, L., Shi, G., & Li, X. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2235847 · Cited by 1,505
“For higher performance, the search of similar patches can also be carried out across different scales at the expense of higher computational complexity, as shown in [31].”
BackgroundA+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution
Timofte, R., De Smet, V., & Van Gool, L. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-16817-3_8 · Cited by 1,408
“natural images consist mainly of flat regions separated by sharp edges) or statistical analysis of many natural images [2–5].”
BackgroundAnchored Neighborhood Regression for Fast Example-Based Super-Resolution
Timofte, R., De, V., & Gool, L. V. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.241 · Cited by 1,351
“These features are almost always calculated from the luminance component of the image, while the color components are interpolated using a regular interpolation algorithm such as bicubic interpolation [9, 18, 17, 4, 3].”
BackgroundMethodRecovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform
Wang, X., Yu, K., Dong, C., & Change Loy, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00070 · Cited by 1,170
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Zhang, K., Zuo, W., & Zhang, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00344 · Cited by 1,124
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Sajjadi, M. S. M., Scholkopf, B., & Hirsch, M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.481 · Cited by 1,058
“In recent years, popular approaches include exemplar-based models that either exploit recurrent patches of different scales within a single image [13, 17, 22, 56] or learn mappings between low and high resolution pairs of image patches in external databases [3, 5, 14, 27, 51, 58, 63].”
BackgroundMethodPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A. P., Tejani, A., Totz, J., Wang, Z., et al. (2016) · arXiv (Cornell University) · doi:10.17863/cam.51996 · Cited by 987
Zero-Shot Super-Resolution Using Deep Internal Learning
Shocher, A., Cohen, N., & Irani, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00329 · Cited by 936
Self-citationFast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
Lai, W.-S., Huang, J.-B., Ahuja, N., & Yang, M.-H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2865304 · Cited by 953
“Several methods [18], [19], [20] exploit the self-similarity property in natural images and construct LR-HR patch pairs”
MethodSinGAN: Learning a Generative Model From a Single Natural Image
Shaham, T. R., Dekel, T., & Michaeli, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00467 · Cited by 890
“Since small structures tend to recur across scales of natural scenes [17], at test time we upsample the LR image by a factor of r and inject it (together with noise) to the last generator, G0.”
BackgroundUhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., & Geiger, A. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00012 · Cited by 924
Ghamisi, P., Yokoya, N., Li, J., Liao, W., Liu, S., Plaza, J., Rasti, B., & Plaza, A. (2017) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2017.2762087 · Cited by 909
“Superresolution techniques can be roughly divided into two types [187]: 1) classical multi-image superresolution, which obtains a high-resolution image (or sequence) from multiple low-resolution images for the same scene with different subpixel shifts, and 2) learning-based superresolution, which learns correspondence…”
BackgroundMulti-Scale Progressive Fusion Network for Single Image Deraining
Jiang, K., Wang, Z., Yi, P., Chen, C., Huang, B., Luo, Y., Ma, J., & Jiang, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00837 · Cited by 795
“Unfortunately, those exploitations fail to make full use of the correlations of multi-scale rain streaks (although restricted to a fixed scale-factor of 2 [10]).”
BackgroundMethodDeep Networks for Image Super-Resolution with Sparse Prior
Wang, Z., Liu, D., Yang, J., Han, W., & Huang, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.50 · Cited by 784
“This simple approach, motivated by the self-similarity based SR approach [13], not only increases the scaling flexibility of our model, but also reduces artifacts for large scaling factors.”
MethodReal-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
Caballero, J., Ledig, C., Aitken, A., Acosta, A., Totz, J., Wang, Z., & Shi, W. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.304 · Cited by 763
Coupled Dictionary Training for Image Super-Resolution
Yang, J., Wang, Z., Lin, Z., Cohen, S., & Huang, T. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2192127 · Cited by 793
Relation-Aware Global Attention for Person Re-Identification
Zhang, Z., Lan, C., Zeng, W., Jin, X., & Chen, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00325 · Cited by 652
Super-resolution: a comprehensive survey
Nasrollahi, K., & Moeslund, T. B. (2014) · Machine Vision and Applications · doi:10.1007/s00138-014-0623-4 · Cited by 684
“[391], [537], [538], [545] the images are first converted to YIQ color space (in [162], [557], [558], [608] to YCbCr).”
MethodInfluentialImage and video upscaling from local self-examples
Freedman, G., & Fattal, R. (2011) · ACM Transactions on Graphics · doi:10.1145/1944846.1944852 · Cited by 679
“Top images show the input bottom images show: (left) input pixels, (middle) output produced by our method, and (right) the results of Glasner et al. [2009].”
BackgroundMethodInfluentialImage Super-Resolution with Non-Local Sparse Attention
Mei, Y., Fan, Y., & Zhou, Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00352 · Cited by 607
Single-Image Super-Resolution: A Benchmark
Yang, C.-Y., Ma, C., & Yang, M.-H. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_25 · Cited by 615
“GBI [11] MC S 364 807 3851 9028 21668 53762”
BackgroundMethodInfluentialVideo Super-Resolution With Convolutional Neural Networks
Kappeler, A., Yoo, S., Dai, Q., & Katsaggelos, A. K. (2016) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2016.2532323 · Cited by 647
Fast and accurate image upscaling with super-resolution forests
Schulter, S., Leistner, C., & Bischof, H. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299003 · Cited by 618
“The task in SISR is to generate a visually pleasing high-resolution output from a single lowresolution input image.”
BackgroundInfluentialToward Real-World Single Image Super-Resolution: A New Benchmark and a New Model
Cai, J., Zeng, H., Yong, H., Cao, Z., & Zhang, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00318 · Cited by 583
“using only two cameras (Canon 5D3 and Nikon D810), the trained model generalizes well to other camera devices such as Sony a7II and mobile phones. 1. Introduction Single image super-resolution (SISR) [15] aims to recover a high-resolution (HR) image from its low-resolution (LR) observation. SISR has been an active res…”
MethodLearning a no-reference quality metric for single-image super-resolution
Ma, C., Yang, C.-Y., Yang, X., & Yang, M.-H. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.12.009 · Cited by 605
Non-Local Recurrent Network for Image Restoration
Liu, D., Wen, B., Fan, Y., Loy, C. C., & Huang, T. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.02919 · Cited by 252
“Self-example based image SR approaches [14, 12] exploit the local self-similarity assumption, and extract LR-HR exemplar pairs merely from the low-resolution image across different scales to predict the high-resolution image.”
Image super-resolution: the techniques, applications, and future
Yue, L., Shen, H., Li, J., Yuan, Q., Zhang, H., & Zhang, L. (2016) · Signal Processing · doi:10.1016/j.sigpro.2016.05.002 · Cited by 554
The Generalized PatchMatch Correspondence Algorithm
Barnes, C., Shechtman, E., Goldman, D. B., & Finkelstein, A. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15558-1_3 · Cited by 530
“For example, examplebased super-resolution can use PatchMatch, using a single [34] or multiple [12] images.”
MethodYou, C., Cong, W., Vannier, M. W., Saha, P. K., Hoffman, E. A., Wang, G., Li, G., Zhang, Y., Zhang, X., Shan, H., et al. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2922960 · Cited by 459
Very Low Resolution Face Recognition Problem
Zou, W. W. W., & Yuen, P. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2162423 · Cited by 488
Seven Ways to Improve Example-Based Single Image Super Resolution
Timofte, R., Rothe, R., & Van Gool, L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.206 · Cited by 449
“[15] use small SR steps to gradually refine the contents up to the desired HR.”
MethodStructure-Preserving Super Resolution With Gradient Guidance
Ma, C., Rao, Y., Cheng, Y., Chen, C., Lu, J., & Zhou, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00779 · Cited by 415
Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
Mei, Y., Fan, Y., Zhou, Y., Huang, L., Huang, T. S., & Shi, H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00573 · Cited by 413
Blind Deblurring Using Internal Patch Recurrence
Michaeli, T., & Irani, M. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_51 · Cited by 403
“[7] showed that most patches in a sharp natural image, recur multiple times in its scaled-down version1.”
BackgroundMethodInfluentialSelf-citationReal-world single image super-resolution: A brief review
Chen, H., He, X., Qing, L., Wu, Y., Ren, C., Sheriff, R. E., & Zhu, C. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.09.005 · Cited by 405
A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution
Peleg, T., & Elad, M. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2305844 · Cited by 407
“Models that are commonly exploited in single image SR methods include image smoothness and geometric regularity of image structures [3]), gradient profile priors [4], self-similarity of image patches within and across different scales in the same image [6], [7], [24], and sparsity – either in the wavelet domain [8], […”
BackgroundTest-Time Training with Self-Supervision for Generalization under Distribution Shifts
Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A. A., & Hardt, M. (2019) · arXiv · doi:10.48550/arxiv.1909.13231 · Cited by 393
“have enough time and space to acknowledge in this draft. We apologize for the omissions and are happy to include additional citations upon request. Learning on test instances. Our idea is inspired by Glasner et al. (2009); Shocher et al. (2018), which learns to perform super-resolution only on a single image, by learn…”
BackgroundSuper-resolution of Sentinel-2 images: Learning a globally applicable deep neural network
Lanaras, C., Bioucas-Dias, J., Galliani, S., Baltsavias, E., & Schindler, K. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.09.018 · Cited by 371
“The literature on self-similarity in image analysis supports such an assumption ( e.g ., Shechtman and Irani, 2007; Glasner et al., 2009), at least over a certain scale range.”
Result“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors
Gandelsman, Y., Shocher, A., & Irani, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01128 · Cited by 355
“, 5x5, 7x7) have been shown to repeat abundantly inside a single natural image [19, 41].”
BackgroundSelf-citationInternal statistics of a single natural image
Zontak, M., & Irani, M. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995401 · Cited by 375
“a (courtesy of [9]) schematically illustrates the notion of “patch recurrence” within a single natural image (similar patches are marked by same colors).”
BackgroundSelf-citationSparse Representation Based Image Interpolation With Nonlocal Autoregressive Modeling
Dong, W., Zhang, L., Lukac, R., & Shi, G. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2231086 · Cited by 362
“Such kind of nonlocal similarity is very helpful to improve the image restoration output, and it has been successfully used in image denoising [31-34], deblurring [35-36] and super-resolution [37-38, 49].”
MethodSuper resolution using edge prior and single image detail synthesis
Tai, Y.-W., Liu, S., Brown, M. S., & Lin, S. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539933 · Cited by 354
“Recent work in [11] used a combined multi-image and learning-based strategy, where the training set is obtained from the low-resolution input itself.”
BackgroundResultInfluentialConvolutional Sparse Coding for Image Super-Resolution
Gu, S., Zuo, W., Xie, Q., Meng, D., Feng, X., & Zhang, L. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.212 · Cited by 347
“For example-based methods, both the external [3, 8, 27] dataset and internal cross-scale relationship [9] can be employed to provide examples of the LR and HR patch pairs.”
MethodNonparametric Blind Super-resolution
Michaeli, T., & Irani, M. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.121 · Cited by 332
“A nonparametric kernel recovery method was presented in Low-resolution image Default kernel Recovered kernel SR of [8] with its default kernel SR of [8] with our recovered kernel Figure 1: Blind SR”
MethodSelf-citationGradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement
Sun, J., Sun, J., Xu, Z., & Shum, H.-Y. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2095871 · Cited by 341
“As the shape parameter is stable to resolution, the remaining problem is to investigate the sharpness dependency between the observed image and the target image for specific application.”
BackgroundFast Direct Super-Resolution by Simple Functions
Yang, C.-Y., & Yang, M.-H. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.75 · Cited by 332
“(a) Bicubic Interpolation (b) Back Projection [8] (c) Shan [5] (d) Proposed”
BackgroundMethodInfluentialSparse Modeling for Image and Vision Processing
Mairal, J. (2014) · now publishers, Inc. eBooks · doi:10.1561/9781680830095 · Cited by 322
Fast Image Super-Resolution Based on In-Place Example Regression
Yang, J., Lin, Z., & Cohen, S. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.141 · Cited by 327
“Freedman and Fattal [6] Glasner et al. [9] Ours Figure 7.”
InfluentialDeep Wavelet Prediction for Image Super-Resolution
Guo, T., Mousavi, H. S., Vu, T. H., & Monga, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.148 · Cited by 301
“For instance, [5, 6, 7, 8, 9] explored the similarity of self-examples, while others mapped the LR to HR patches with use of external samples [10, 11, 12, 13, 14, 15, 16, 17].”
BackgroundEfficient and Explicit Modelling of Image Hierarchies for Image Restoration
Li, Y., Fan, Y., Xiang, X., Demandolx, D., Ranjan, R., Timofte, R., & Van Gool, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01753 · Cited by 302
“Inspired by that, later works have been developed to utilize the repetitive patterns in a non-local range for image denoising [10] and super-resolution [22].”
MethodLi, M., Hsu, W., Xie, X., Cong, J., & Gao, W. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2968472 · Cited by 321
“This idea was widely used in applications such as image denoising [46], texture synthesis [47], super-resolution [48], and inpainting [49].”
MethodUltra-Resolving Face Images by Discriminative Generative Networks
Yu, X., & Porikli, F. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_20 · Cited by 308
“[24,28,29,26] exploit self-similarity of patches in an input image to generate high resolution patches.”
BackgroundMethodSparse Modeling for Image and Vision Processing
Ponce, J., Mairal, J., Bach, F., Image, S. M., Processing, V., Hal, H. I., & Supérieure, E. N. (2014) · Cited by 335
Single image super-resolution using Gaussian process regression
He, H., & Siu, W.-C. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995713 · Cited by 294
“Recently, it has been statistically shown in [8] that small patches (e.”
BackgroundMethodInfluentialDeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., & Ganguly, A. R. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098004 · Cited by 281
“a scene. „e most successful approaches to SR have been shown to be patch based (or example-based) techniques, achieving state-of-theart performance [10, 35, 39]. Originally proposed by Glasner et al. [14], patch based methods exploit self-similarity between images to produce exemplar patches. „is approach has evolved…”
BackgroundXiao, M., Zheng, S., Liu, C., Wang, Y., He, D., Ke, G., Bian, J., Lin, Z., & Liu, T.-Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_8 · Cited by 249
A Fully Progressive Approach to Single-Image Super-Resolution
Wang, Y., Perazzi, F., McWilliams, B., Sorkine-Hornung, A., Sorkine-Hornung, O., & Schroers, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00131 · Cited by 262
Component Divide-and-Conquer for Real-World Image Super-Resolution
Wei, P., Xie, Z., Lu, H., Zhan, Z., Ye, Q., Zuo, W., & Lin, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58598-3_7 · Cited by 259
Zhang, X., Chen, Q., Ng, R., & Koltun, V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00388 · Cited by 260
“Several approaches use patch matching to search for similar patches in a training dataset or in the image itself [8, 10, 12].”
BackgroundODE-Inspired Network Design for Single Image Super-Resolution
He, X., Mo, Z., Wang, P., Liu, Y., Yang, M., & Cheng, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00183 · Cited by 258
Atkinson, P. M. (2013) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2012.04.012 · Cited by 264
Robust Single Image Super-Resolution via Deep Networks With Sparse Prior
Liu, D., Wang, Z., Wen, B., Yang, J., Han, W., & Huang, T. S. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2564643 · Cited by 266
“This practice is commonly adopted in the self-similarity based methods [8], [9], [14], but is not so popular in other cases for the fear of error accumulation during repetitive upscaling.”
BackgroundMethodLearning a blind measure of perceptual image quality
Tang, H., Joshi, N., & Kapoor, A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995446 · Cited by 251
“The cross-scale distribution of wavelet coefficient magnitude is also a meaningful feature, as high quality image often show self-similarity across scales [8].”
BackgroundDeep Network Cascade for Image Super-resolution
Cui, Z., Chang, H., Shan, S., Zhong, B., & Chen, X. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_4 · Cited by 255
“Since natural image patches recur many times within an image and even across different scales [10], we can always find some similar patches for a given patch.”
BackgroundMethodInfluentialCrossNet: An End-to-End Reference-Based Super Resolution Network Using Cross-Scale Warping
Zheng, H., Ji, M., Wang, H., Liu, Y., & Fang, L. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_6 · Cited by 244
Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems
Ding, K., Ma, K., Wang, S., & Simoncelli, E. P. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01419-7 · Cited by 224
“(a) High-resolution image, (b-h) are the super-resolution results computed using bicubic interpolation, Glasner09 (Glasner et al. 2009), Yang13 (Yang andYang 2013),EDSR(Lim et al.”
Unfolding the Alternating Optimization for Blind Super ResolutionPreprint
Luo, Z., Huang, Y., Shang, L., Wang, L., & Tan, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.02631 · Cited by 246
“In [13, 29], the blur kernel is used to downsample images and synthesize training samples, which can be used to train a specific model for given kernel and LR image.”
MethodTransformer-Based Multistage Enhancement for Remote Sensing Image Super-Resolution
Lei, S., Shi, Z., & Mo, W. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3136190 · Cited by 236
“We further use back-projection technology [47, 48] to reduce the blocking effect in the preliminary results, so as to obtain the final HR reconstructed images.”
MethodLearning to Super-Resolve Blurry Face and Text Images
Xu, X., Sun, D., Pan, J., Zhang, Y., Pfister, H., & Yang, M.-H. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.36 · Cited by 235
“1The results have been kindly provided by the authors using [29] for kernel estimation and [11] for super-resolution.”
MethodPyramid Attention Network for Image Restoration
Mei, Y., Fan, Y., Zhang, Y., Yu, J., Zhou, Y., Liu, D., Fu, Y., Huang, T. S., & Shi, H. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01843-5 · Cited by 263
“Several self-similarity based approaches Glasner et al. (2009); Freedman and Fattal (2011); Singh and Ahuja (2014) were first proposed for image super-resolution, where they restore image details by borrowing high-frequency details from self-recurrences at larger scales.”
BackgroundResultInfluentialBrain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks
Chen, Y., Xie, Y., Zhou, Z., Shi, F., Christodoulou, A., & Li, D. (2018) · eScholarship (California Digital Library) · Cited by 228
Brain MRI super resolution using 3D deep densely connected neural networks
Chen, Y., Xie, Y., Zhou, Z., Shi, F., Christodoulou, A. G., & Li, D. (2018) · 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) · doi:10.1109/isbi.2018.8363679 · Cited by 222
“Therefore, a SISR [2] technique which needs only one LR scan to provide an HR output is an attractive approach to address this problem.”
MethodDeep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
Heckel, R., & Hand, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.03982 · Cited by 166
Bidirectional recurrent convolutional networks for multi-frame super-resolution
Huang, Y., Wang, W., & Wang, L. (2015) · neural information processing systems · Cited by 222
Improved Techniques for Training Single-Image GANs
Hinz, T., Fisher, M., Wang, O., & Wermter, S. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00134 · Cited by 203
“prior, many tasks such as inpainting [43,46], denoising [53], deblurring [37], retargeting [34,35], and segmentation [11] can be solved with only a single image. In particular, image super-resolution [44,20,12,40,4] and editing [7,9,15,36,42,33] from a single image have been shown to be successful and a large body of…”
BackgroundReal-Time Artifact-Free Image Upscaling
Giachetti, A., & Asuni, N. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2136352 · Cited by 216
“A possible way to avoid the use of training images has been proposed in [8] where patch recurrence in single images at different scales and with different subpixel alignment is used in a framework similar to classic multiframe super resolution.”
A Pansharpening Method Based on the Sparse Representation of Injected Details
Vicinanza, M. R., Restaino, R., Vivone, G., Dalla Mura, M., & Chanussot, J. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2014.2331291 · Cited by 218
“Consequently, the suitability of this approach for the problem at hand derives from the consideration that the patterns tend to repeat several times within an image and the number of recurrence is smaller for high variance zones, or in other terms, for those characterized by the presence of a greater amount of spatial…”
BackgroundMethodInfluentialVideo Super-Resolution via Bidirectional Recurrent Convolutional Networks
Huang, Y., Wang, W., & Wang, L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2701380 · Cited by 209
“Recently, variousmethods have been proposed to handle this problem, which can be classified into two categories: 1) single-image SR [7], [14], [15], [24], [27], [46], [52] super resolves each low-resolution video frame independently, and 2) multi-frame SR [2], [3], [32], [32], [34], [38] super resolves a low-resolutio…”
BackgroundPatch Based Synthesis for Single Depth Image Super-Resolution
Mac Aodha, O., Campbell, N. D. F., Nair, A., & Brostow, G. J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33712-3_6 · Cited by 211
“[19] exploit patch repetition across and within scales of the low resolution input to find candidates.”
BackgroundAccurate Blur Models vs. Image Priors in Single Image Super-resolution
Efrat, N., Glasner, D., Apartsin, A., Nadler, B., & Levin, A. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.352 · Cited by 200
“Kernel sensitivity of Glasner et al [8].”
BackgroundInfluentialEdge-Guided Single Depth Image Super Resolution
Xie, J., Feris, R. S., & Sun, M.-T. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2501749 · Cited by 198
“The work of [11] proposes to search for similar image patches across multiple downscaled versions of the image with no need to collect training image data beforehand.”
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.