Single image super-resolution via BM3D sparse coding
The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
In this paper, a novel single image super-resolution (SISR) algorithm is proposed. It is based on the BM3D (Block-Matching and 3D filtering) paradigm, where both sparsity and nonlocal patch self-similarity priors are utilized. The algorithm is derived from a variational formulation of the problem and has a structure typical for iterative back-projection super-resolution methods. They are characterized by updating high-resolution image which is calculated using the previous estimate and upsampled low-resolution error. The developed method is thoroughly compared with the state-of-the-art SISR both for noiseless and noisy data, demonstrating superior performance objectively and subjectively.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Image denoising by sparse 3-D transform-domain collaborative filtering
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.901238 · Cited by 9,283
Self-citationLearning 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
Image Super-Resolution Via Sparse Representation
Yang, J., Wright, J., Huang, T. S., & Ma, Y. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2050625 · Cited by 5,217
On 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 · cited 2×
“A sparsity prior has been applied in [2], [5], where coef¿cients of sparse representation of LR image patch have been used to produce the corresponding HR image patch.”
MethodSuper-resolution from a single image
Glasner, D., Bagon, S., & Irani, M. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459271 · Cited by 1,889 · cited 1×
“Internal methods based on image selfsimilarity across the scales have been proposed in [9], [10].”
MethodA+: 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
Anchored 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 · cited 3×
“Some recent SISRmethods, including anchored neighborhood regression [6], [7] and deep-learning methods [8] based”
BackgroundMethodInfluentialMotion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency
Irani, M., & Peleg, S. (1993) · Journal of Visual Communication and Image Representation · doi:10.1006/jvci.1993.1030 · Cited by 805 · cited 2×
“It has a structural similarity to the back-projection (e.g. [1], [3], [11]) with two main differences: (1) ¿ltering at each iteration is applied to HR images instead of ¿ltering upsampled low-resolution errors (differences), and (2) the BM3D, image adaptive and very ef¿cient denoising is applied…”
BackgroundImage and video upscaling from local self-examples
Freedman, G., & Fattal, R. (2011) · ACM Transactions on Graphics · doi:10.1145/1944846.1944852 · Cited by 679 · cited 1×
“Internal methods based on image selfsimilarity across the scales have been proposed in [9], [10].”
MethodBM3D Frames and Variational Image Deblurring
Danielyan, A., Katkovnik, V., & Egiazarian, K. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2176954 · Cited by 611 · cited 2×
“It can be veri¿ed using [13] that for the given BM3D frames © and ª the solution (7) and the equation x n K = ªμ n are precisely correspond to the hard thresholding stage of the BM3D ¿lter [12].”
MethodSelf-citation
Research works printed but not linked: 3
- dai, 2007, Bilateral backprojection for single image super resolution, IEEE Conf on Mult and Expo ICME, 1039
- fernandez-granda, 2013, Super-resolution and Compressed Sensing, SIAM News, 46
- timofte, 2013, Anchored neighborhood regression for fast example-based superresolution, Proc IEEE Int Conf on Computer Vision, 1920
Cited by
Learning Deep CNN Denoiser Prior for Image Restoration
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.300 · Cited by 2,116
“Inspired by the method proposed in [24] which iteratively updates a back-projection [33] step and a denoising step for SISR, we use the following back-projection iteration to solve Eqn.”
BackgroundMethodLearning 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
Plug-and-Play Image Restoration With Deep Denoiser Prior
Zhang, K., Li, Y., Zuo, W., Zhang, L., Van Gool, L., & Timofte, R. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3088914 · Cited by 1,113
“In [25], a similar method equipped with CBM3D denoiser prior was proposed for single image superresolution (SISR).”
BackgroundMethodDeep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels
Zhang, K., Zuo, W., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00177 · Cited by 408
“During the past few years, a flurry of plug-and-play works have been developed from the following aspects: 1) different variable splitting algorithms, such as half-quadratic splitting (HQS) algorithm [1], alternating direction method of multipliers (ADMM) algorithm [8], FISTA [4], and primal-dual algorithm [11, 42]; 2)…”
MethodDisentangling Light Fields for Super-Resolution and Disparity Estimation
Wang, Y., Wang, L., Wu, G., Yang, J., An, W., Yu, J., & Guo, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3152488 · Cited by 321
“Alain et al. extended BM3D [35] filtering to LFBM5D for both denoising [36] and spatial SR [33].”
MethodSpatial-Angular Interaction for Light Field Image Super-Resolution
Wang, Y., Wang, L., Yang, J., An, W., Yu, J., & Guo, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58592-1_18 · Cited by 208
Light Field Image Super-Resolution Using Deformable Convolution
Wang, Y., Yang, J., Wang, L., Ying, X., Wu, T., An, W., & Guo, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3042059 · Cited by 177
“proposed LFBM5D for LF image denoising [53] and LF image SR [24] by extending BM3D filtering [54] to LFs.”
MethodCong, R., Sheng, H., Yang, D., Cui, Z., & Chen, R. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3282465 · Cited by 152
Learning Deep Gradient Descent Optimization for Image Deconvolution
Gong, D., Zhang, Z., Shi, Q., van den Hengel, A., Shen, C., & Zhang, Y. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2968289 · Cited by 148
“Table IX shows the PSNR values of the denoising results of the classical method CBM3D [57], learning based method TNRD [49] and IRCNN [13] and the proposed method.”
MethodResultRegularization by Denoising via Fixed-Point Projection (RED-PRO)
Cohen, R., Elad, M., & Milanfar, P. (2021) · SIAM Journal on Imaging Sciences · doi:10.1137/20m1337168 · Cited by 168
Light Field Super-Resolution via LFBM5D Sparse Coding
Alain, M., & Smolić, A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451162 · Cited by 92
“75 as in [10], and we use the bicubic filter to upsample the residual error.”
BackgroundMethodInfluentialSingle Image Super-Resolution Based on Wiener Filter in Similarity Domain
Cruz, C., Mehta, R., Katkovnik, V. Y., & Egiazarian, K. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2779265 · Cited by 80
Self-citationSpatial-Angular Versatile Convolution for Light Field Reconstruction
Cheng, Z., Liu, Y., & Xiong, Z. (2022) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2022.3225650 · Cited by 67
“Inspired by BM3D for single image super-resolution [51], Alain and Smolic [49] proposed an algorithm that alternates between”
MethodSuper-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning
Tirer, T., & Giryes, R. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2920250 · Cited by 64
“Some have relied on specific prior image models, such as sparsity [6–8, 10, 16, 17 Our work follows the P&P approach, introduced in [29], which suggests leveraging excellent performance of denoising algorithms for solving other inverse imaging problems that can be formulated as a cost function,…”
MethodAbbasi, A., Monadjemi, A., Fang, L., & Rabbani, H. (2018) · Journal of Biomedical Optics · doi:10.1117/1.jbo.23.3.036011 · Cited by 59
“To tackle with heavier and more realistic noise, two interpolation methods based on the well-known block-matching and 3D filtering (BM3D) sparse representation model are recently introduced.(37,38) Although the reconstruction results are excellent, these methods use internal BM3D dictionaries that are learned from the…”
MethodDense Dual-Attention Network for Light Field Image Super-Resolution
Mo, Y., Wang, Y., Xiao, C., Yang, J., & An, W. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3121679 · Cited by 47
“Alain et al. [17] employed an LFBM5D filter to achieve LF image SR based on SRBM3D [45].”
Deep Light Field Super-Resolution Using Frequency Domain Analysis and Semantic Prior
Chen, Y., Jiang, G., Jiang, Z., Yu, M., & Ho, Y. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3106775 · Cited by 47
Deep Residual Network for Joint Demosaicing and Super-Resolution
Zhou, R., Achanta, R., & Susstrunk, S. E. (2018) · Color and Imaging Conference · doi:10.2352/issn.2169-2629.2018.26.75 · Cited by 42
Image Super-Resolution With Parametric Sparse Model Learning
Li, Y., Dong, W., Xie, X., Shi, G., Wu, J., & Li, X. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2837865 · Cited by 35
“Various image priors - ranging from piecewise smoothness to sparsity and structured sparsity constraints - have been proposed for image SR [12], [13], [15]–[19].”
BackgroundHyperspectral Image Denoising via Low-Rank Representation and CNN Denoiser
Sun, H., Liu, M., Zheng, K., Yang, D., Li, J., & Gao, L. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3138564 · Cited by 35
A Novel Sharpening Approach for Superresolving Multiresolution Optical Images
Paris, C., Bioucas‐Dias, J. M., & Bruzzone, L. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2867284 · Cited by 31
“The authors would like to thank A. Foi for many valuable discussions, D. A. Foi, V. Katkovnik, and K. Egiazarian for kindly providing the CMB3D code, and Q. Wang, W. Shi, Z. Li, and P. M. Atkinson for providing the code of the synthetized version of the ATPRK method.”
BackgroundDisparity-Guided Light Field Image Super-Resolution via Feature Modulation and Recalibration
Liu, G., Yue, H., Li, K., & Yang, J. (2023) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2023.3284408 · Cited by 29
“Rossi and Frossard [31] designed an approach based on graph optimization for LF spatial SR. Alain and Smolic [11] introduced LFBM5D, which is an extension of BM3D [32] for LF spatial SR. 2) CNN-Based Methods: CNN-based methods for LF spatial SR can be divided into two categories, i.e., explicit disparity estimation-ba…”
BackgroundParameswaran, S., Deledalle, C., Denis, L., & Nguyen, T. Q. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2866691 · Cited by 33
Single image super-resolution approaches in medical images based-deep learning: a survey
El‐Shafai, W., Ali, A. M., El‐Nabi, S. A., El‐Rabaie, E. M., & El‐Samie, F. E. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16197-w · Cited by 29
“Egiazarian first used the BM3D paradigm in 2007 [31] and then in 2015 [30] for SR.”
A compendious study of super-resolution techniques by single image
Pandey, G., & Ghanekar, U. (2018) · Optik · doi:10.1016/j.ijleo.2018.03.103 · Cited by 26
Learning Deep CNN Denoiser Priors for Depth Image Inpainting
Li, Z., & Wu, J. (2019) · Applied Sciences · doi:10.3390/app9061103 · Cited by 28
Gradient-based discriminative modeling for blind image deblurring
Shao, W., Lin, Y., Liu, Y.-Y., Wang, L., Ge, Q., Bao, B., & Li, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.093 · Cited by 25
Super-Resolution of Optical Coherence Tomography Images by Scale Mixture Models
Daneshmand, P. G., Rabbani, H., & Mehridehnavi, A. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2984896 · Cited by 22
“A nonlocal sparse reconstruction model has recently been offered, using the nonlocal patch self-similarities to enhance the reconstruction [48]–[51].”
BackgroundMethodMiShape: Accurate Human Silhouettes and Body Joints from Commodity Millimeter-Wave Devices
Adhikari, A., Regmi, H., Sur, S., & Nelakuditi, S. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550300 · Cited by 30
“, use interpolation and fixed models to upsample the images [63, 64, 107].”
MethodWu, P., Ding, M., & Zheng, Y. (2023) · IET Intelligent Transport Systems · doi:10.1049/itr2.12383 · Cited by 17
Classification of priors and regularization techniques appurtenant to single image super-resolution
Pandey, G., & Ghanekar, U. (2019) · The Visual Computer · doi:10.1007/s00371-019-01729-z · Cited by 15
“NLMalongwithsparsitystructured[59,62] isbetterforSISRreconstruction these three leads to mixed priors.”
BackgroundMethodDeep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations
Umer, R. M., Foresti, G. L., & Micheloni, C. (2019) · International Conference on Distributed Smart Cameras · doi:10.1145/3349801.3349823 · Cited by 16
“Model-based optimization methods such as non-local self-similarity prior [10, 21, 24], sparsity prior [32] and denoiser prior [2, 12, 35], have powerful image priors to reconstruct HR images, but their optimization procedure is computationally expensive.”
MethodZhou, D., Liu, Y., Li, X., & Zhang, C. (2020) · The Visual Computer · doi:10.1007/s00371-020-02007-z · Cited by 13
“BM3D-SR [14] enlarge the image by combining Wiener filtering in transform domain and iterative back projection framework.”
MethodCompressive sensed video recovery via iterative thresholding with random transforms
Belyaev, E., Codreanu, M., Juntti, M. J., & Egiazarian, K. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.0661 · Cited by 13
Self-citationHybrid sparsity learning for image restoration: An iterative and trainable approach
Wu, F., Dong, W., Huang, T., Shi, G., Cheng, S., & Li, X. (2020) · Signal Processing · doi:10.1016/j.sigpro.2020.107751 · Cited by 13
Error Concealment for 3-D DWT Based Video Codec Using Iterative Thresholding
Belyaev, E., Forchhammer, S. O., & Codreanu, M. (2017) · IEEE Communications Letters · doi:10.1109/lcomm.2017.2697428 · Cited by 8
“In this letter, we use a quadratic function [12], i.”
BackgroundMethodHidane, M., Gheche, M. E., Aujol, J., Berthoumieu, Y., & Deledalle, C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2571061 · Cited by 8
“The setting we have just described may also arise in the context of digital photography when one uses a digital camera to capture an image of a given scene, and then uses the optical zoom of the same camera to capture a subset of the same scene.”
Reivew of Light Field Image Super-Resolution
Yu, L., Ma, Y., Hong, S., & Chen, K. (2022) · Electronics · doi:10.3390/electronics11121904 · Cited by 7
Learning Parametric Sparse Models for Image Super-Resolution
Li, Y., Dong, W., Xie, X., Shi, G., Li, X., & Xu, D. (2016) · neural information processing systems · Cited by 7
Image Restoration Based on End-to-End Unrolled Network
Tao, X., Zhou, H., & Chen, Y. (2021) · Photonics · doi:10.3390/photonics8090376 · Cited by 7
“The proposed SISR solver in [66] iterates 35 times, and the IRCNN [61] takes 30 iterations to deblur.”
MethodA Criminisi-DnCNN Model-Based Image Inpainting Method
Li, Z., Zhu, Y., & Wang, Y. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/9780668 · Cited by 5
“In literature [26], combining BM3D and convolutional neural network, the “extraction” and “aggregation” layers were used to model the block matching phase in BM3D to form BM3D-net and perform the image denoising task.”
MethodH.265/HEVC Decoding via Iterative Recovery From Incomplete Quantized Measurements
Mahfod, K., & Belyaev, E. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3624678 · Cited by 4
Motion JPEG Decoding via Iterative Thresholding and Motion-Compensated Deflickering
Belyaev, E., Bie, L., & Korhonen, J. (2020) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp48831.2020.9287147 · Cited by 4
“Inthis paper, we consider M-JPEG decoding as a signal recovery task from incomplete measurements, which is well-know in compressive sensing [9] and its particular applications, such as super-resolution imaging [10] and error-concealment [11].”
MethodLu, X., Lü, X., & Zuo, Y. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.05.021 · Cited by 4
MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution
Chao, W., Duan, F.-Q., Guo, Y., & Wang, G.-H. (2024) · IEEE transactions on multimedia · doi:10.1109/tmm.2024.3521781 · Cited by 4
“Alain et al. [31] extended the BM3D [32] filter to LFBM5D for LF de-noising and spatial SR. Rossi et al. [33] developed a graph-based approach to achieve spatial super-resolution through graph optimization.”
Hierarchical feature fusion network for light field spatial super-resolution
Hua, X., Wang, M., Su, B., & Liu, X. (2022) · The Visual Computer · doi:10.1007/s00371-021-02327-8 · Cited by 3
“filter SR-BM3D [9] and the LF denoising filter LFBM5D for LF image SR.”
MethodSuper-resolution Reconstruction of Dual Regular Items Infrared Image Based on Deep Plug-and-Play
Zhang, X., & Yu, L. (2020) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1145/3408127.3408162 · Cited by 3
“In [12 ], the authors proposed a zero-shot super-resolution (ZSSR) method which trains image-specific DNN on the testing LR image and can also take the degradation parameters, such as the estimated blur kernel, to improve the performance.”
BackgroundPandey, G., & Ghanekar, U. (2021) · Transactions on computer systems and networks · doi:10.1007/978-981-16-1681-5_7 · Cited by 2
A Single Historical Painting Super-Resolution via a Reference-Based Zero-Shot Network
Shi, H., Xu, D., Zhang, H., & Yue, Y. (2021) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.d.210503.002 · Cited by 2
“Model-based optimization methods can flexibly achieve super-resolution reconstruction either by employing Hopfield neural networks [7] or by using global self-similar information [8], sparse priors [9], denoising priors [10], etc.”
MethodLight Field Spatial Super-resolution via Multi-level Perception and View Reorganization
Mao, Y., Tong, Z., Zheng, X., Zhou, X., Zhang, Y., & Liu, D. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.01405111 · Cited by 2
“Among them, LFBM5D [10] extends the BM3D [11] filtering to 5D to provide more prior information and thus improve the super-resolution performance.”
BackgroundVelumani, R., Bama, S., & Jose, M. V. (2021) · Springer eBooks · doi:10.1007/978-3-030-67921-7_10 · Cited by 1
Zhang, H., Chen, F., Huang, L., Wei, W., & Peng, Z. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105139 · Cited by 1
Revisiting Subspace Disentangling for Light Field Spatial Super-Resolution
Zhang, F., Wang, Y., Wang, X., Liang, Z., Wang, L., Tian, L., & Yang, J. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3661516 · Cited by 1
“Early approaches primarily relied on handcrafted image processing techniques, including image reprojection [16], [17], prior-based modeling [18], [19], and patch-based matching [20], [21], [22].”
A Transferred Graph Laplacian Regularization Approach for Color Image Denoising
Hou, X., Ge, H., Jiang, X., Cao, Y., & Meng, Y. (2023) · International Conference on Communication, Image and Signal Processing (CCISP) · doi:10.1109/ccisp59915.2023.10355853 · Cited by 1
Shao, W., Deng, H.-S., Ge, Q., & Wang, L. (2023) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-022-00863-7
“…idea in Zoran and Weiss (2011); Venkatakrishnan et al., 2013), later extended and harnessed in Sreehari et al. (1512); Rond et al., 2016; Egiazarian & Katkovnik, 2015; Romano et al., 2017; Brifman et al., 2016; Chan et al., 2017; Shao et al., 2018), solving (10) can be in fact…”
BackgroundLiu, H., Ma, J., Chen, S., Dong, L. F., Huang, L., & Xu, R. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3398-5_40
Li, Z., & Zhao, W. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02361-6
Deep learning for inverse problems and application to omni-directional imaging
Fermanian, R. (2023) · theses.fr (ABES) · doi:10.70675/32276fcazbbadz4565z9235za0c4d6c198ec
Metadata
- Authors
- Egiazarian, K., & Katkovnik, V.
- Affiliations
- Tampere University of Technology (FI)
- Venue
- 2015 23rd European Signal Processing Conference (EUSIPCO)
- Publisher
- IEEE
- Published
- 2015-08
- Pages
- 2849-2853
- OpenAlex
- W2202027014
- Cited by
- 58
- References
- 16
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 1 · 2023: 8 · 2022: 6 · 2021: 9 · 2020: 10 · 2019: 5 · 2018: 9 · 2017: 3 · 2016: 2
- FWCI
- 1.90
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- European Signal Processing Conference (EUSIPCO) (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, BM3D, sparse coding, variational formulation, image denoising
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.