{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:00:17Z","timestamp":1780675217903,"version":"3.54.1"},"reference-count":195,"publisher":"Emerald","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,5]]},"abstract":"<jats:p>Recent advances in neural signal processing led to significant improvements in the performance of learned image\/video restoration and super-resolution (SR). An important benefit of data-driven deep learning approaches to image processing is that neural models can be optimized for any differentiable loss function, including perceptual loss functions, leading to perceptual image\/video restoration and SR, which cannot be easily handled by traditional model-based methods.<\/jats:p>\n                  <jats:p>We start with a brief problem statement and a short discussion on traditional vs. data-driven solutions. We next review recent advances in neural architectures, such as residual blocks, dense connections, residual-in-residual dense blocks, residual blocks with generative neurons, self-attention and visual transformers. We then discuss loss functions and evaluation (assessment) criteria for image\/video restoration and SR, including fidelity (distortion) and perceptual criteria, and the relation between them, where we briefly review the perception vs. distortion trade-off.<\/jats:p>\n                  <jats:p>We can consider learned image\/video restoration and SR as learning either a nonlinear regressive mapping from degraded to ideal images based on the universal approximation theorem, or a generative model that captures the probability distribution of ideal images. We first review regressive inference via residual and\/or dense convolutional networks (ConvNet). We also show that using a new architecture with residual blocks based on a generative neuron model can outperform classical residual ConvNets in peak-signal-to-noise ratio (PSNR). We next discuss generative inference based on adversarial training, such as SRGAN and ESRGAN, which can reproduce realistic textures, or based on normalizing flow such as SRFlow by optimizing log-likelihood. We then discuss problems in applying supervised training to real-life restoration and SR, including overfitting image priors and overfitting the degradation model seen in the training set. We introduce multiple-model SR and real-world SR (from unpaired training data) formulations to overcome these problems. Integration of traditional model-based methods and deep learning for non-blind restoration\/SR is introduced as another solution to model overfitting in supervised learning.<\/jats:p>\n                  <jats:p>In learned video restoration and SR (VSR), we first discuss how to best exploit temporal correlations in video, including sliding temporal window vs. recurrent architectures for propagation, and aligning frames in the pixel domain using optical flow vs. in the feature space using deformable convolutions. We next introduce early fusion with feature-space alignment, employed by the EDVR network, which obtains excellent PSNR performance. However, it is well-known that videos with the highest PSNR may not be the most appealing to humans, since minimizing the mean-square error may result in blurring of details. We then address perceptual optimization of VSR models to obtain natural texture and motion. Although perception-distortion tradeoff has been well studied for images, few works address perceptual VSR. In addition to using perceptual losses, such as MS-SSIM, LPIPS, and\/or adversarial training, we also discuss explicit loss functions\/criteria to enforce and evaluate temporal consistency. We conclude with a discussion of open problems.<\/jats:p>","DOI":"10.1561\/0600000100","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T09:35:13Z","timestamp":1651743313000},"page":"1-110","source":"Crossref","is-referenced-by-count":4,"title":["Deep Learning for Image\/Video Restoration and Super-resolution"],"prefix":"10.1108","volume":"13","author":[{"given":"A. Murat","family":"Tekalp","sequence":"first","affiliation":[{"name":"Ko\u00e7 University Department of Electrical and Electronics Engineering, ,","place":["Turkey"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2022,5,5]]},"reference":[{"key":"2026032615263948500_ref001","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2017.150","article-title":"NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Agustsson","year":"2017"},{"issue":"3","key":"2026032615263948500_ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3390462","article-title":"A deep journey into superresolution: A survey","volume":"53","author":"Anwar","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2026032615263948500_ref003","first-page":"2716","article-title":"Explorable Super Resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Bahat","year":"2020"},{"key":"2026032615263948500_ref004","doi-asserted-by":"crossref","DOI":"10.1109\/AFGR.2000.840616","article-title":"Hallucinating faces","volume-title":"Proc. of the IEEE Int. Conf. on Automatic Face and Gesture Recognition","author":"Baker","year":"2000"},{"key":"2026032615263948500_ref005","first-page":"284","article-title":"Blind super-resolution kernel estimation using an internal-GAN","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Bell-Kligler","year":"2019"},{"key":"2026032615263948500_ref006","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00338","article-title":"Attention augmented convolutional networks","volume-title":"Int. Conf. on Computer Vision (ICCV)","author":"Bello","year":"2019"},{"key":"2026032615263948500_ref007","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s11760-017-1166-8","article-title":"On the use of deep learning for blind image quality assessment","volume":"12","author":"Bianco","year":"2018","journal-title":"Signal, Image, and Video Processing (SIViP)"},{"key":"2026032615263948500_ref008","article-title":"The 2018 PIRM Challenge on Perceptual Image Superresolution","volume-title":"Euro. Conf. Comp. Vision (ECCV) Workshop","author":"Blau","year":"2018"},{"key":"2026032615263948500_ref009","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00652","article-title":"The perception-distortion tradeoff","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Blau","year":"2018"},{"key":"2026032615263948500_ref010","article-title":"Toward A Practical Perceptual Video Quality Metric","volume-title":"Netflix Technology (2016-06-06), Last Accessed: 2021-07-01","author":"Blog","year":"2016"},{"key":"2026032615263948500_ref011","article-title":"Dynamic filter networks","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Brabandere","year":"2016"},{"key":"2026032615263948500_ref012","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2005.38","article-title":"A non-local algorithm for image denoising","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Buades","year":"2005"},{"key":"2026032615263948500_ref013","article-title":"Realtime video super-resolution with spatio-temporal networks and motion compensation","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR)","author":"Caballero","year":"2017"},{"key":"2026032615263948500_ref014","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00274","article-title":"NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshop","author":"Cai","year":"2019"},{"key":"2026032615263948500_ref015","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00318","article-title":"Toward real-world single image super-resolution: A new benchmark and a new model","volume-title":"IEEE Int. Conf. on Computer Vision","author":"Cai","year":"2019"},{"issue":"3","key":"2026032615263948500_ref016","first-page":"307","article-title":"iSeeBetter: Spatiotemporal video super-resolution using recurrent generative back-projection networks","volume":"6","author":"Chadha","year":"2020","journal-title":"Springer Jour. of Computational Visual Media, Tsinghua University Press"},{"key":"2026032615263948500_ref017","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.00491","article-title":"BasicVSR: The search for essential components in video super-resolution and beyond","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recognition (CVPR)","author":"Chan","year":"2021"},{"key":"2026032615263948500_ref018","article-title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","author":"Chan","year":"2021"},{"issue":"9","key":"2026032615263948500_ref019","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1109\/TIP.2007.901820","article-title":"VSNR: A wavelet-based visual signal-to-noise ratio for natural images","volume":"16","author":"Chandler","year":"2007","journal-title":"IEEE Trans. on Image Processing"},{"key":"2026032615263948500_ref020","article-title":"High performance convolutional neural networks for document processing","volume-title":"Int. Workshop on Frontiers in Handwriting Recognition","author":"Chellapilla","year":"2006"},{"key":"2026032615263948500_ref021","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.01212","article-title":"Pre-trained Image Processing Transformer","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Chen","year":"2021"},{"key":"2026032615263948500_ref022","article-title":"VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge","volume-title":"arXiv preprint arXiv:2003.02115","author":"Chen","year":"2020"},{"key":"2026032615263948500_ref023","first-page":"1","article-title":"Fast video superresolution using artificial neural networks","volume-title":"Int. Symp. Commun. Syst. Netw. Digital Signal Proc. (CSNDSP)","author":"Cheng","year":"2012"},{"key":"2026032615263948500_ref024","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW53098.2021.00054","article-title":"Perceptual image quality assessment with transformers","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Cheon","year":"2021"},{"key":"2026032615263948500_ref025","first-page":"1724","article-title":"Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation","volume-title":"Empirical Methods in Natural Language Processing (EMNLP)","author":"Cho","year":"2014"},{"issue":"4","key":"2026032615263948500_ref026","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1145\/3386569.3392457","article-title":"Learning temporal coherence via self supervision for GAN-based video generation","volume":"39","author":"Chu","year":"2020","journal-title":"ACM Trans. on Graphics (TOG)"},{"key":"2026032615263948500_ref027","article-title":"Flexible, High Performance Convolutional Neural Networks for Image Classification","volume-title":"Int. Joint Conf. on Artificial Intelligence (IJCAI), Barcelona, Spain","author":"Ciresan","year":"2011"},{"key":"2026032615263948500_ref028","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1109\/ICCV.2017.89","article-title":"Deformable Convolutional Networks","volume-title":"IEEE Int. Conf. on Computer Vision (ICCV)","author":"Dai","year":"2017"},{"key":"2026032615263948500_ref029","first-page":"179","volume-title":"The visible difference predictor: An algorithm for the assessment of image fidelity","author":"Daly","year":"1993"},{"key":"2026032615263948500_ref030","doi-asserted-by":"crossref","first-page":"5612","DOI":"10.1109\/TIP.2020.2984879","article-title":"No-reference video quality assessment using natural spatiotemporal scene statistics","volume":"29","author":"Dendi","year":"2020","journal-title":"IEEE Trans. Image Proc."},{"key":"2026032615263948500_ref031","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2020.3045810","article-title":"Image quality assessment: Unifying structure and texture similarity","volume-title":"IEEE Trans. on Patt. Anal. Mach. Intel. (PAMI)","author":"Ding","year":"2020"},{"issue":"4","key":"2026032615263948500_ref032","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1007\/s11263-020-01419-7","article-title":"Comparison of Image Quality Models for Optimization of Image Processing Systems","volume":"129","author":"Ding","year":"2021","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"2026032615263948500_ref033","article-title":"Density estimation using real NVP","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Dinh","year":"2017"},{"key":"2026032615263948500_ref034","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10593-2_13","article-title":"Learning a Deep Convolutional Network for Image Super-Resolution","volume-title":"European Conf. on Computer Vision (ECCV)","author":"Dong","year":"2014"},{"issue":"2","key":"2026032615263948500_ref035","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image Super-Resolution Using Deep Convolutional Networks","volume":"38","author":"Dong","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2026032615263948500_ref036","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Int. Conf. Learning Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"2026032615263948500_ref037","first-page":"14","article-title":"From linear adaptive filtering to nonlinear information processing","volume-title":"IEEE Signal Processing Magazine","author":"Erdogmus","year":"2006"},{"key":"2026032615263948500_ref038","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00269","article-title":"An empirical investigation of efficient spatio-temporal modeling in video restoration","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision Workshop (ICCVW)","author":"Fan","year":"2019"},{"key":"2026032615263948500_ref039","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00248","article-title":"Suppressing Model Overfitting for Image Super-Resolution Networks","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR) Workshops","author":"Feng","year":"2019"},{"issue":"4","key":"2026032615263948500_ref040","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1109\/TIP.2008.2011760","article-title":"A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB)","volume":"18","author":"Ferzli","year":"2009","journal-title":"IEEE Trans. on Image Processing"},{"issue":"2","key":"2026032615263948500_ref041","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/38.988747","article-title":"Example-based superresolution","volume":"22","author":"Freeman","year":"2002","journal-title":"IEEE Computer Graphics and Applications"},{"issue":"4","key":"2026032615263948500_ref042","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF00344251","article-title":"Neocognitron : A self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position","volume":"36","author":"Fukushima","year":"1980","journal-title":"Biological Cybernetics"},{"key":"2026032615263948500_ref043","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-66823-5_4","article-title":"AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision Workshop (ICCVW)","author":"Fuoli","year":"2020"},{"key":"2026032615263948500_ref044","article-title":"Efficient video superresolution through recurrent latent space propagation","volume-title":"Int. Conf. Comp. Vision (ICCV) Workshops","author":"Fuoli","year":"2019"},{"key":"2026032615263948500_ref045","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neucom.2017.01.054","article-title":"Deepsim: Deep similarity for image quality assessment","volume":"257","author":"Gao","year":"2017","journal-title":"Neurocomputing"},{"key":"2026032615263948500_ref046","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2026032615263948500_ref047","first-page":"2672","article-title":"Generative adversarial nets","volume":"2","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026032615263948500_ref048","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW53098.2021.00077","article-title":"NTIRE 2021 Challenge on perceptual image quality assessment","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Gu","year":"2021"},{"key":"2026032615263948500_ref049","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00170","article-title":"Blind super-resolution with iterative kernel correction","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Gu","year":"2019"},{"key":"2026032615263948500_ref050","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00685","article-title":"Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet?","volume-title":"IEEE\/CVF Conf. on Comp. Vis. Patt. Recog. (CVPR)","author":"Hara","year":"2018"},{"key":"2026032615263948500_ref051","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00402","article-title":"Recurrent back-projection network for video super-resolution","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Haris","year":"2019"},{"key":"2026032615263948500_ref052","article-title":"Deep back-projection networks for single image super-resolution","volume-title":"IEEE Trans. on Patt. Anal. and Mach. Intel. (PAMI)","author":"Haris","year":"2021"},{"key":"2026032615263948500_ref053","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"IEEE\/CVF Computer Vision and Patt. Recog. (CVPR)","author":"He","year":"2016"},{"key":"2026032615263948500_ref054","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"Identity mappings in deep residual networks","volume-title":"European Conf. on Comp. Vision (ECCV)","author":"He","year":"2016"},{"key":"2026032615263948500_ref055","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9054089","article-title":"XPSNR: A low-complexity extension of the perceptually weighted peak signal-to-noise-ratio for high-resolution video quality assessment","volume-title":"ICASSP","author":"Helmrich","year":"2020"},{"issue":"6","key":"2026032615263948500_ref056","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1038\/s41593-019-0377-4","article-title":"Perceptual straightening of natural videos","volume":"22","author":"Henaff","year":"2019","journal-title":"Nature Neuroscience"},{"key":"2026032615263948500_ref057","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Heusel","year":"2017"},{"issue":"8","key":"2026032615263948500_ref058","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"2026032615263948500_ref059","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks, Pergamon Press"},{"key":"2026032615263948500_ref060","first-page":"3464","article-title":"Local Relation Networks for Image Recognition","volume-title":"IEEE\/CVF Int. Conf. on Computer Vision (ICCV)","author":"Hu","year":"2019"},{"key":"2026032615263948500_ref061","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Huang","year":"2017"},{"key":"2026032615263948500_ref062","article-title":"Bidirectional recurrent convolutional networks for multi-Frame super-resolution","volume":"28","author":"Huang","year":"2015","journal-title":"Neural Information Processing Systems (NIPS)"},{"issue":"4","key":"2026032615263948500_ref063","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1109\/TPAMI.2017.2701380","article-title":"Video super-resolution via bidirectional recurrent convolutional networks","volume":"40","author":"Huang","year":"2018","journal-title":"IEEE Trans. on Patt. Anal. and Mach. Intel"},{"key":"2026032615263948500_ref064","doi-asserted-by":"crossref","unstructured":"Ignatov, A., N.Kobyshev, R.Timofte, K.Vanhoey, and L. V.Gool. (2017). \u201cDSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks\u201d. arXiv: 1704.02470 [cs.CV].","DOI":"10.1109\/ICCV.2017.355"},{"issue":"3","key":"2026032615263948500_ref065","first-page":"231","article-title":"Improving Resolution by Image Registration","volume":"53","author":"Irani","year":"1991","journal-title":"CVGIP: Graphical Models and Image Processing"},{"key":"2026032615263948500_ref066","doi-asserted-by":"crossref","DOI":"10.5244\/C.34.8","article-title":"Revisiting temporal modeling for video super-resolution","volume-title":"British Mach. Vision Conf. (BMVC)","author":"Isobe","year":"2020"},{"key":"2026032615263948500_ref067","first-page":"769","article-title":"Natural image denoising with convolutional networks","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Jain","year":"2008"},{"key":"2026032615263948500_ref068","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00230","article-title":"DenseNet with deep residual channel-attention blocks for single image super resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR) Workshops","author":"Jang","year":"2019"},{"key":"2026032615263948500_ref069","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW50498.2020.00241","article-title":"Real-World Super-Resolution via Kernel Estimation and Noise Injection","volume-title":"The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Ji","year":"2020"},{"key":"2026032615263948500_ref070","article-title":"Deep video superresolution network using dynamic upsampling filters without explicit motion compensation","volume-title":"IEEE\/CVF Conf. on Comp. Vis. Patt. Recog. (CVPR)","author":"Jo","year":"2018"},{"key":"2026032615263948500_ref071","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW53098.2021.00046","article-title":"SRFlow-DA: Super-resolution using normalizing flow with deep convolutional block","volume-title":"IEEE\/CVF Conf. Comp. Vision and Patt. Recog. (CVPR) Workshop","author":"Jo","year":"2021"},{"key":"2026032615263948500_ref072","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46475-6_43","article-title":"Perceptual losses for real-time style transfer and super-resolution","volume-title":"European Conf. on Comp. Vision (ECCV)","author":"Johnson","year":"2016"},{"key":"2026032615263948500_ref073","article-title":"The relativistic discriminator: A key element missing from standard GAN","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Jolicoeur-Martineau","year":"2019"},{"key":"2026032615263948500_ref074","doi-asserted-by":"crossref","first-page":"2167","DOI":"10.1109\/LSP.2021.3118639","article-title":"Improving the visual quality of video frame prediction models using the perceptual straightening hypothesis","volume":"28","author":"Kancharla","year":"2021","journal-title":"IEEE Signal Processing Letters"},{"key":"2026032615263948500_ref075","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/TIP.2021.3130541","article-title":"Completely blind quality assessment of user generated video content","volume":"31","author":"Kancharla","year":"2022","journal-title":"IEEE Trans. on Image Processing"},{"key":"2026032615263948500_ref076","first-page":"1733","article-title":"Convolutional neural networks for no-reference image quality assessment","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Kang","year":"2014"},{"issue":"2","key":"2026032615263948500_ref077","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/TCI.2016.2532323","article-title":"Video super resolution with convolutional neural networks","volume":"2","author":"Kappeler","year":"2016","journal-title":"IEEE Trans. on Computational Imaging"},{"key":"2026032615263948500_ref078","volume-title":"IEEE Int. Conf. on Image Processing","author":"Kele\u015f","year":"2021"},{"key":"2026032615263948500_ref079","article-title":"On the computation of PSNR for a set of images and video","volume-title":"Picture Coding Symp. (PCS)","author":"Kele\u015f","year":"2021"},{"key":"2026032615263948500_ref080","article-title":"Accurate image superresolution using very deep convolutional networks","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR)","author":"Kim","year":"2016"},{"key":"2026032615263948500_ref081","article-title":"3DSRNet: Video superresolution using 3D convolutional neural networks","volume-title":"IEEE Int. Conf. on Image Proc. (ICIP)","author":"Kim","year":"2019"},{"key":"2026032615263948500_ref082","first-page":"10236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Kingma","year":"2018"},{"key":"2026032615263948500_ref083","article-title":"Auto-encoding variational Bayes","volume-title":"Int. Conf. Learning Representations (ICLR)","author":"Kingma","year":"2014"},{"key":"2026032615263948500_ref084","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.neunet.2021.02.028","article-title":"Self-organized Operational Neural Networks with Generative Neurons","volume":"140","author":"Kiranyaz","year":"2021","journal-title":"Neural Networks"},{"key":"2026032615263948500_ref085","first-page":"514","volume-title":"Proc. of the EUSIPCO","author":"Kirmemis","year":"2018"},{"key":"2026032615263948500_ref086","first-page":"3964","article-title":"Normalizing flows: An introduction and review of current methods","volume-title":"IEEE Trans. on Patt. Anal. and Mach. Intel. (PAMI)","author":"Kobyzev","year":"2021"},{"key":"2026032615263948500_ref087","first-page":"1910","article-title":"Resource efficient 3D convolutional neural networks","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision Workshop (ICCVW)","author":"K\u00f6p\u00fckl\u00fc","year":"2019"},{"key":"2026032615263948500_ref088","volume-title":"Multi-Model and Multi-Stage Learned Image Super-Resolution","author":"Korkmaz","year":"2021"},{"key":"2026032615263948500_ref089","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Krizhevsky","year":"2012"},{"key":"2026032615263948500_ref090","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.618","article-title":"Deep Laplacian pyramid networks for fast and accurate super-resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR)","author":"Lai","year":"2017"},{"issue":"4","key":"2026032615263948500_ref091","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural computation"},{"key":"2026032615263948500_ref092","article-title":"Photorealistic single image super-resolution using a generative adversarial network","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Ledig","year":"2017"},{"key":"2026032615263948500_ref093","first-page":"2093","article-title":"DynaVSR: Dynamic adaptive blind video super-resolution","volume-title":"IEEE\/CVF Winter Conf. on Appl. of Comp. Vision","author":"Lee","year":"2021"},{"key":"2026032615263948500_ref094","doi-asserted-by":"crossref","first-page":"4474","DOI":"10.1109\/TIP.2020.2972118","article-title":"Learning a Deep Dual Attention Network for Video Super-Resolution","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. on Image Proc"},{"key":"2026032615263948500_ref095","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW54120.2021.00210","article-title":"SwinIR: Image Restoration Using Swin Transformer","volume-title":"IEEE Int. Conf. on Computer Vision (ICCV) Workshops","author":"Liang","year":"2021"},{"key":"2026032615263948500_ref096","first-page":"531","article-title":"Video superresolution via deep draft-ensemble learning","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision (ICCV)","author":"Liao","year":"2015"},{"key":"2026032615263948500_ref097","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2017.151","article-title":"Enhanced deep residual networks for single image super-resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vis. Patt. Recog. (CVPR) Workshop","author":"Lim","year":"2017"},{"key":"2026032615263948500_ref098","doi-asserted-by":"crossref","DOI":"10.1109\/APSIPA.2017.8282261","article-title":"Deep recurrent Resnet for video super-resolution","volume-title":"Proc. of APSIPA Annual Summit and Conf","author":"Lim","year":"2017"},{"key":"2026032615263948500_ref099","unstructured":"Liu, A.\n            et al.\n           (2021a). \u201cBlind Image Super-Resolution: A Survey and Beyond\u201d. arXiv: 2107.03055 [cs.CV]."},{"issue":"1","key":"2026032615263948500_ref100","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s11263-006-0029-5","article-title":"Face hallucination: Theory and practice","volume":"75","author":"Liu","year":"2007","journal-title":"Int. J. Comput. Vision"},{"issue":"7","key":"2026032615263948500_ref101","doi-asserted-by":"crossref","first-page":"3432","DOI":"10.1109\/TIP.2018.2820807","article-title":"Learning temporal dynamics for video super-resolution: A deep learning approach","volume":"27","author":"Liu","year":"2018","journal-title":"IEEE Trans. on Image Processing"},{"key":"2026032615263948500_ref102","unstructured":"Liu, H.\n            et al.\n           (2020). \u201cVideo super resolution based on deep learning: A comprehensive survey\u201d. arXiv: 2007.12928 [cs.CV]."},{"key":"2026032615263948500_ref103","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.118","article-title":"RankIQA: Learning from Rankings for No-reference Image Quality Assessment","volume-title":"Int. Conf. on Comp. Vision (ICCV)","author":"Liu","year":"2017"},{"key":"2026032615263948500_ref104","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01170","article-title":"Swin Transformer V2: Scaling Up Capacity and Resolution","volume-title":"IEEE\/CVF Int. Conf. on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2022"},{"key":"2026032615263948500_ref105","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","volume-title":"IEEE\/CVF Int. Conf. on Computer Vision (ICCV)","author":"Liu","year":"2021"},{"issue":"7","key":"2026032615263948500_ref106","doi-asserted-by":"crossref","first-page":"3312","DOI":"10.1109\/TIP.2019.2895768","article-title":"Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution","volume":"28","author":"Lucas","year":"2019","journal-title":"IEEE Trans. on Image Proc"},{"key":"2026032615263948500_ref107","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2019.00442","article-title":"AIM 2019 Challenge on real-world image super-resolution: Methods and results","volume-title":"Int. Conf. Comp. Vision (ICCV) Workshops","author":"Lugmayr","year":"2019"},{"key":"2026032615263948500_ref108","unstructured":"Lugmayr, A.\n            et al.\n           (2020a). \u201cNTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results\u201d. arXiv: 2005.01996 [eess.IV]."},{"key":"2026032615263948500_ref109","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58558-7_42","article-title":"SRFlow: Learning the super-resolution space with onrmalizing flow","volume-title":"Euro. Conf. Comp. Vision (ECCV)","author":"Lugmayr","year":"2020"},{"key":"2026032615263948500_ref110","article-title":"Unfolding the alternating optimization for blind super resolution","volume":"34","author":"Luo","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2026032615263948500_ref111","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2016.12.009","article-title":"Learning a no-reference quality metric for single-image super-resolution","volume-title":"Comp. Vision and Image Understand (CVIU)","author":"Ma","year":"2017"},{"key":"2026032615263948500_ref112","volume-title":"German Conf. on Pattern Recognition (GCPR)","author":"Makansi","year":"2017"},{"key":"2026032615263948500_ref113","first-page":"2480","article-title":"An optical flow-based full reference video quality assessment algorithm","volume-title":"IEEE Trans. Image Proc","author":"Manasa","year":"2016"},{"issue":"4","key":"2026032615263948500_ref114","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1109\/TIT.1974.1055250","article-title":"The effects of a visual fidelity criterion on the encoding of images","volume":"20","author":"Mannos","year":"1974","journal-title":"IEEE Trans. Inform. Theory"},{"key":"2026032615263948500_ref115","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bulletin of Mathematical Biophysics"},{"key":"2026032615263948500_ref116","volume-title":"Perceptrons : An Introduction to Computational Geometry","author":"Minsky","year":"1969"},{"issue":"12","key":"2026032615263948500_ref117","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-Reference Image Quality Assessment in the Spatial Domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. on Image Processing"},{"issue":"3","key":"2026032615263948500_ref118","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","article-title":"Making a completely blind image quality analyzer","volume":"20","author":"Mittal","year":"2013","journal-title":"IEEE Signal Processing Letters"},{"key":"2026032615263948500_ref119","first-page":"18","article-title":"Algorithm unrolling","volume-title":"IEEE Signal Processing Magazine","author":"Monga","year":"2021"},{"key":"2026032615263948500_ref120","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00251","article-title":"NTIRE 2019 Challenge on Video Deblurring and Super-Resolution: Dataset and Study","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR) Workshops","author":"Nah","year":"2019"},{"key":"2026032615263948500_ref121","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00250","article-title":"NTIRE 2019 Challenge on Video Super-Resolution: Methods and Results","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR) Workshops","author":"Nah","year":"2019"},{"issue":"6","key":"2026032615263948500_ref122","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.1016\/j.patcog.2004.01.013","article-title":"GPU implementation of neural networks","volume":"37","author":"Oh","year":"2004","journal-title":"Pattern Recognition"},{"key":"2026032615263948500_ref123","first-page":"4811","article-title":"Deep blind video super-resolution","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision (ICCV)","author":"Pan","year":"2021"},{"key":"2026032615263948500_ref124","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"Jou. of Machine Learning Research"},{"key":"2026032615263948500_ref125","first-page":"72","article-title":"Theoretical foundations of deep learning via sparse representations","volume-title":"IEEE Signal Processing Magazine","author":"Papyan","year":"2018"},{"issue":"8","key":"2026032615263948500_ref126","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1109\/83.605404","article-title":"Superresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time","volume":"6","author":"Patti","year":"1997","journal-title":"IEEE Trans. on Image Processing"},{"key":"2026032615263948500_ref127","article-title":"Perceptual video super-resolution with enhanced temporal consistency","volume-title":"arXiv preprint arXiv:1807.07930","author":"P\u00e9rez-Pellitero","year":"2019"},{"key":"2026032615263948500_ref128","article-title":"Photorealistic video super-resolution","volume-title":"ECCV Workshops (PIRM)","author":"P\u00e9rez-Pellitero","year":"2018"},{"key":"2026032615263948500_ref129","article-title":"On Between-coefficient Contrast Masking of DCT Basis Functions","volume-title":"Int. Workshop on Video Processing and Quality Metrics for Consumer Electronics (VPQM), Scottsdale, Arizona","author":"Ponomarenko","year":"2007"},{"key":"2026032615263948500_ref130","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00194","article-title":"PieAPP: Perceptual image-error assessment through pairwise preference","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Prashnani","year":"2018"},{"key":"2026032615263948500_ref131","article-title":"Benefiting from Bicubically Down-Sampled Images for Learning Real-World Image Super-Resolution","volume-title":"IEEE\/CVF WACV","author":"Rad","year":"2021"},{"key":"2026032615263948500_ref132","article-title":"Stand-Alone Self-Attention in Vision Models","volume-title":"(NeurIPS)","author":"Ramachandran","year":"2019"},{"key":"2026032615263948500_ref133","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.01196","article-title":"Vision Transformers for Dense Prediction","volume-title":"IEEE Int. Conf. on Computer Vision (ICCV)","author":"Ranftl","year":"2021"},{"key":"2026032615263948500_ref134","first-page":"1530","article-title":"Variational inference with normalizing flows","volume":"37","author":"Rezende","year":"2015","journal-title":"Int. Conf. on Machine Learning (ICML)"},{"key":"2026032615263948500_ref135","unstructured":"Rippel, O. and R. P.Adams. (2013). \u201cHigh-dimensional probability estimation with deep density models\u201d. arXiv: 1302.5125 [cs.CV]."},{"key":"2026032615263948500_ref136","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Comp. Assisted Interven. (MICCAI)"},{"issue":"6","key":"2026032615263948500_ref137","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1037\/h0042519","article-title":"The perceptron: A probabilistic model for information storage and organization in the brain","volume":"65","author":"Rosenblatt","year":"1958","journal-title":"Psychological Review"},{"key":"2026032615263948500_ref138","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representation by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2026032615263948500_ref139","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00693","article-title":"Frame-recurrent video super-resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vis. Patt. Recog. (CVPR)","author":"Sajjadi","year":"2018"},{"key":"2026032615263948500_ref140","article-title":"Improved Techniques for Training GANs","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Salimans","year":"2016"},{"issue":"2","key":"2026032615263948500_ref141","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1109\/TIP.2009.2034992","article-title":"Motion tuned spatiotemporal quality assessment of natural videos","volume":"19","author":"Seshadrinathan","year":"2010","journal-title":"IEEE Trans. on Image Processing"},{"issue":"2","key":"2026032615263948500_ref142","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/TIP.2005.859378","article-title":"Image information and visual quality","volume":"15","author":"Sheikh","year":"2006","journal-title":"IEEE Trans. on Image Processing"},{"issue":"12","key":"2026032615263948500_ref143","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1109\/TIP.2005.859389","article-title":"An information fidelity criterion for image quality assessment using natural scene statistics","volume":"14","author":"Sheikh","year":"2005","journal-title":"IEEE Trans. on Image Processing"},{"key":"2026032615263948500_ref144","first-page":"3531","article-title":"Efficient attention: Attention with linear complexities","volume-title":"IEEE\/CVF Winter Conf. on Applications of Computer Vision (WACV)","author":"Shen","year":"2021"},{"key":"2026032615263948500_ref145","first-page":"1874","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","volume-title":"IEEE\/CVF Conf. on Comp. Vis. Patt. Recog. (CVPR)","author":"Shi","year":"2016"},{"key":"2026032615263948500_ref146","first-page":"802","volume-title":"Int. Conf. on Neural Information Processing Systems","author":"Shi","year":"2015"},{"key":"2026032615263948500_ref147","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00329","article-title":"\u201cZero-Shot\u201d Super-Resolution using Deep Internal Learning","volume-title":"IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)","author":"Shocher","year":"2018"},{"key":"2026032615263948500_ref148","first-page":"2377","article-title":"Training very deep networks","volume":"2","author":"Srivastava","year":"2015","journal-title":"Int. Conf. on Neural Information Processing Systems (NIPS)"},{"key":"2026032615263948500_ref149","first-page":"172443","article-title":"Local-global fusion network for video super-resolution","volume-title":"IEEE Access","author":"Su","year":"2020"},{"key":"2026032615263948500_ref150","article-title":"Detail-revealing deep video superresolution","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision (ICCV)","author":"Tao","year":"2017"},{"key":"2026032615263948500_ref151","volume-title":"Digital Video Processing","author":"Tekalp","year":"2015"},{"key":"2026032615263948500_ref152","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/BF01816547","article-title":"Quantitative analysis of artifacts in linear space-invariant image restoration","volume":"1","author":"Tekalp","year":"1990","journal-title":"Multidimensional Systems and Signal Processing"},{"key":"2026032615263948500_ref153","first-page":"3360","article-title":"TDAN: Temporally deformable alignment network for video super-resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recognition (CVPR)","author":"Tian","year":"2020"},{"key":"2026032615263948500_ref154","volume-title":"Solution of Ill-posed Problems","author":"Tikhonov","year":"1977"},{"key":"2026032615263948500_ref155","article-title":"NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Timofte","year":"2017"},{"key":"2026032615263948500_ref156","article-title":"NTIRE 2018 Challenge on single image superresolution: Methods and results","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR) Workshops","author":"Timofte","year":"2018"},{"key":"2026032615263948500_ref157","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.206","article-title":"Seven ways to improve example-based single image super resolution","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Timofte","year":"2016"},{"key":"2026032615263948500_ref158","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.514","article-title":"Image super-resolution using dense skip connections","volume-title":"Int. Conf. on Comp. Vision (ICCV)","author":"Tong","year":"2017"},{"key":"2026032615263948500_ref159","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","volume-title":"Int. Conf. Comp. Vision (ICCV)","author":"Tran","year":"2015"},{"issue":"2","key":"2026032615263948500_ref160","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TASSP.1984.1164297","article-title":"The feasible solution in signal restoration","volume":"32","author":"Trussell","year":"1984","journal-title":"IEEE Trans. on Acoustics, Speech, and Signal Processing"},{"key":"2026032615263948500_ref161","first-page":"1867","article-title":"Deep image prior","volume-title":"Int. Jour. of Computer Vision","author":"Ulyanov","year":"2020"},{"key":"2026032615263948500_ref162","article-title":"FVD : A new metric for video generation","volume-title":"Int. Conf. Learn. Represent. (ICLR) Workshop on Deep Generative Models for Highly Structured Data","author":"Unterthiner","year":"2019"},{"key":"2026032615263948500_ref163","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2019.00247","article-title":"EDVR: Video restoration with enhanced deformable convolutional networks","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Wang","year":"2019"},{"key":"2026032615263948500_ref164","first-page":"7794","article-title":"Non-local neural networks","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Wang","year":"2018"},{"key":"2026032615263948500_ref165","article-title":"ESRGAN: Enhanced super-resolution generative adversarial networks","volume-title":"European Conf. Comp. Vision (ECCV) Workshop","author":"Wang","year":"2018"},{"issue":"1","key":"2026032615263948500_ref166","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MSP.2008.930649","article-title":"Mean squared error: Love it or leave it?","volume":"26","author":"Wang","year":"2009","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"2026032615263948500_ref167","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. on Image Processing"},{"issue":"10","key":"2026032615263948500_ref168","doi-asserted-by":"crossref","first-page":"3365","DOI":"10.1109\/TPAMI.2020.2982166","article-title":"Deep learning for image super-resolution: A survey","volume":"43","author":"Wang","year":"2021","journal-title":"IEEE Trans. on Patt. Anal. and Mach. Intel. (PAMI)"},{"key":"2026032615263948500_ref169","first-page":"1398","article-title":"Multiscale Structural Similarity for Image Quality Assessment","volume-title":"Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, USA","author":"Wang","year":"2003"},{"key":"2026032615263948500_ref170","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01716","article-title":"Uformer: A General U-Shaped Transformer for Image Restoration","volume-title":"IEEE\/CVF Int. Conf. on Computer Vision and Pattern Recognition (CVPR)","author":"Wang","year":"2022"},{"issue":"10","key":"2026032615263948500_ref171","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/5.58337","article-title":"Backpropagation through time: What it does and how to do it","volume":"78","author":"Werbos","year":"1990","journal-title":"Proceedings of the IEEE"},{"key":"2026032615263948500_ref172","volume-title":"Learning likelihoods with conditional normalizing flows","author":"Winkler","year":"2019"},{"issue":"4","key":"2026032615263948500_ref173","first-page":"1","article-title":"TempoGAN: A temporally coherent, volumetric GAN for super-resolution fluid flow","volume":"37","author":"Xie","year":"2018","journal-title":"ACM Trans. on Graphics (TOG)"},{"key":"2026032615263948500_ref174","first-page":"496","article-title":"Unified dynamic convolutional network for super-resolution with variational degradations","volume":"12","author":"Xu","year":"2020","journal-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)"},{"issue":"8","key":"2026032615263948500_ref175","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1007\/s11263-018-01144-2","article-title":"Video Enhancement with Task-Oriented Flow","volume":"127","author":"Xue","year":"2019","journal-title":"Int. Jour. of Computer Vision (IJCV)"},{"key":"2026032615263948500_ref176","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00583","article-title":"Learning Texture Transformer Network for Image Super-Resolution","volume-title":"CVPR","author":"Yang","year":"2020"},{"key":"2026032615263948500_ref177","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.cviu.2017.09.002","article-title":"Video super-resolution based on spatial-temporal recurrent residual networks","volume":"168","author":"Yang","year":"2018","journal-title":"Computer Vision and Image Understanding"},{"key":"2026032615263948500_ref178","first-page":"4781","article-title":"Real-world video super-resolution: A benchmark dataset and a decomposition based learning scheme","volume-title":"IEEE\/CVF Int. Conf. on Comp. Vision (ICCV) Workshop","author":"Yang","year":"2021"},{"key":"2026032615263948500_ref179","article-title":"No-reference image quality assessment using visual codebook","volume-title":"IEEE Int. Conf. Image Process. (ICIP)","author":"Ye","year":"2011"},{"key":"2026032615263948500_ref180","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1109\/LSP.2020.3013518","article-title":"Deformable 3D convolution for video super-resolution","volume":"27","author":"Ying","year":"2020","journal-title":"IEEE Signal Processing Letters"},{"key":"2026032615263948500_ref181","article-title":"Wide activation for efficient image and video super-resolution","volume-title":"British Mach. Vision Conf., Cardiff Univ","author":"Yu","year":"2019"},{"key":"2026032615263948500_ref182","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2018.00113","article-title":"Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Yuan","year":"2018"},{"key":"2026032615263948500_ref183","article-title":"mixup: Beyond Empirical Risk Minimization","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Zhang","year":"2018"},{"key":"2026032615263948500_ref184","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW50498.2020.00254","article-title":"NTIRE 2020 Challenge on perceptual extreme super-resolution: Methods and results","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR) Workshops","author":"Zhang","year":"2020"},{"key":"2026032615263948500_ref185","article-title":"Plug-and-play image restoration with deep denoiser prior","volume-title":"IEEE Trans. on Patt. Anal. and Mach. Intel. (PAMI)","author":"Zhang","year":"2021"},{"key":"2026032615263948500_ref186","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00344","article-title":"Learning a single convolutional super-resolution network for multiple degradations","volume-title":"EEE\/CVF Conf. CVPR","author":"Zhang","year":"2018"},{"key":"2026032615263948500_ref187","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00328","article-title":"Deep unfolding network for image super-resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Zhang","year":"2020"},{"key":"2026032615263948500_ref188","first-page":"3929","article-title":"Learning deep CNN denoiser prior for image restoration","volume-title":"IEEE Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Zhang","year":"2017"},{"issue":"6","key":"2026032615263948500_ref189","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1109\/TCSVT.2017.2654543","article-title":"Residual Networks of Residual Networks: Multilevel Residual Networks","volume":"28","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Circuits and Systems for Video Tech"},{"issue":"8","key":"2026032615263948500_ref190","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.1109\/TIP.2015.2426416","article-title":"A feature-enriched completely blind image quality evaluator","volume":"24","author":"Zhang","year":"2015","journal-title":"IEEE Trans. on Image Processing"},{"key":"2026032615263948500_ref191","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/CVPR.2018.00068","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog.(CVPR)","author":"Zhang","year":"2018"},{"key":"2026032615263948500_ref192","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00319","article-title":"RankSRGAN: Generative adversarial networks with ranker for image super-resolution","volume-title":"Int. Conf. on Comp. Vision (ICCV)","author":"Zhang","year":"2019"},{"key":"2026032615263948500_ref193","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_18","article-title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","volume-title":"IEEE\/CVF ECCV","author":"Zhang","year":"2018"},{"key":"2026032615263948500_ref194","first-page":"2472","article-title":"Residual dense network for image super-resolution","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Zhang","year":"2018"},{"key":"2026032615263948500_ref195","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01415","article-title":"MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment","volume-title":"IEEE\/CVF Conf. on Comp. Vision and Patt. Recog. (CVPR)","author":"Zhua","year":"2020"}],"container-title":["Foundations and Trends\u00ae in Computer Graphics and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftcgv\/article-pdf\/13\/1\/1\/10865056\/0600000100en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftcgv\/article-pdf\/13\/1\/1\/10865056\/0600000100en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T14:09:11Z","timestamp":1777471751000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftcgv\/article\/13\/1\/1\/1319349\/Deep-Learning-for-Image-Video-Restoration-and"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,5]]},"references-count":195,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,5,5]]}},"URL":"https:\/\/doi.org\/10.1561\/0600000100","relation":{},"ISSN":["1572-2740","1572-2759"],"issn-type":[{"value":"1572-2740","type":"print"},{"value":"1572-2759","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,5]]}}}