浏览全部资源
扫码关注微信
Received：26 December 2024，
Revised：11 February 2025，
Accepted：2025-02-25，
Published Online：26 February 2025，
移动端阅览
高分辨率的视觉感知对场景的理解、分析等工作十分重要，但在真实场景下受限于拍摄条件、成像设备成本和系统光学器件、电路噪声和传感器的灵敏度等因素，图像往往伴随着各种降质因素影响，表现出模糊、低分辨率等特性。因此，挖掘和利用低分辨率图像中包含的相关信息，利用超分辨重建的方式提高成像分辨率具有十分重要的研究价值。为此，本文系统地分析了国际国内近年来在真实场景下图像超分辨重建领域的重要研究进展，包括问题构造和降质建模、超分辨领域常用数据集与评价指标、传统真实场景下超分辨重建、真实场景下基于监督学习的超分辨重建以及真实场景下基于无监督学习的超分辨重建技术等。其中，问题构造和降质建模部分讨论了降质成像过程及模型化方法。数据集与评价指标部分讨论了超分辨领域常见的合成数据集、真实场景数据集以及定量和定性评价方法。传统超分辨重建部分探讨了早期的超分辨重建方法，包括内插法和基于重建的方法等。基于监督学习的超分辨重建部分则以退化形式为区分，从退化未知与退化已知两个角度进行梳理，探讨如何利用监督信息指导模型参数学习。基于无监督学习的超分辨重建部分则从无监督角度分析讨论低分辨率图像信息的利用，以及退化模型的建模与估计。论文详细综述了上述研究的挑战性，梳理了国内外技术发展脉络和前沿动态。最后，根据上述分析展望了真实场景下图像超分辨技术的发展方向。
High-resolution visual perception plays a pivotal role in numerous computer vision tasks， including scene understanding， object recognition， and image analysis， as it enables the extraction of finer details that are critical for accurate and meaningful interpretations of visual data. Applications such as autonomous driving， medical imaging， remote sensing， and surveillance heavily rely on the clarity and richness of high-resolution images. However， in real-world scenarios， achieving high-quality image capture is often constrained by various practical factors. Limitations in shooting conditions， such as low lighting， motion， and adverse weather， can introduce noise， blurriness， and distortion to images. Furthermore， the cost and limitations of imaging equipment， including optical system components， sensor sensitivity， and circuit noise， often result in degraded image quality， characterized by low resolution and loss of detail. These challenges pose significant hurdles for downstream applications， necessitating methods that can enhance and recover the resolution and quality of degraded images. One promising solution to address these challenges is image super-resolution （SR）， a technique designed to reconstruct high-resolution （HR） images from low-resolution （LR） inputs. Super-resolution holds immense research value， as it not only enhances visual quality but also boosts the performance of various downstream tasks， particularly in resource-constrained scenarios where high-end imaging devices are unavailable. By extracting and utilizing the latent information present in LR images， SR techniques aim to bridge the gap between degraded and high-quality visuals， making it an active area of investigation within the fields of computer vision and image processing.This paper provides a comprehensive review of the recent advancements in image super-resolution reconstruction， focusing on progress made in addressing real-world challenges. It systematically explores the major research contributions both domestically and internationally over recent years， categorizing them into several key areas. These include problem formulation and degradation modeling， commonly used datasets and evaluation metrics in SR research， traditional super-resolution reconstruction methods， and modern approaches based on supervised and unsupervised learning. Through this structured analysis， the paper aims to offer valuable insights into the evolution of SR techniques， highlight persistent challenges， and provide an outlook on future development trends in this field. The first section of the paper addresses problem formulation and degradation modeling， which serve as the foundational step in SR research. Degradation modeling involves understanding the various processes that contribute to image degradation， such as noise， compression， and optical distortions. Researchers have proposed a variety of approaches to address this， ranging from controlled synthetic degradation modeling for benchmarking to advanced data-driven methods that learn degradation patterns directly from real-world datasets. The second section discusses datasets and evaluation metrics， which are critical for the development and validation of SR methods. Synthetic datasets， such as Set5， Set14， and DIV2K， are widely used for controlled experiments because they provide paired LR-HR image pairs generated using predefined degradation models. However， these datasets often fail to represent the complexities of real-world scenarios. In response， real-world datasets such as RealSR， DRealSR， and City100 are increasingly being utilized to train and evaluate SR models under practical conditions. The paper also examines commonly used evaluation metrics， including quantitative measures like peak signal-to-noise ratio （PSNR） and structural similarity index measure （SSIM）， as well as perceptual-based metrics like learned perceptual image patch similarity （LPIPS）. These metrics help assess the fidelity and visual quality of reconstructed images， although they often have limitations in capturing subjective human perception. The third section delves into traditional super-resolution reconstruction methods， which laid the foundation for modern SR research. Early methods primarily relied on interpolation techniques， such as bicubic interpolation， which are simple and computationally efficient but fail to recover high-frequency details. Reconstruction-based methods， on the other hand， use prior knowledge about image structures to restore missing details. Techniques like sparse representation and dictionary learning have shown promise in this area， but their reliance on handcrafted features and assumptions about image properties limits their performance in complex real-world scenarios. The fourth section explores supervised learning-based super-resolution reconstruction， which has gained immense popularity with the advent of deep learning. Supervised SR methods rely on paired LR-HR datasets to train neural networks that learn the mapping between low- and high-resolution images. However， supervised SR methods face challenges in handling unknown degradation. To address this， researchers have proposed degradation-aware networks and domain adaptation techniques that aim to bridge the gap between synthetic and real-world data， ensuring better generalization to practical scenarios. The fifth section discusses unsupervised learning-based super-resolution reconstruction， which is particularly valuable in scenarios where paired LR-HR data is unavailable. Unsupervised methods leverage techniques such as generative adversarial networks （GANs） and cycle-consistent loss functions to learn mappings between LR and HR domains without explicit supervision. For example， CycleGAN-based models align the distributions of LR and HR images， enabling effective SR reconstruction. Self-supervised learning approaches， which utilize auxiliary tasks or pretext objectives， have also shown promise in leveraging unpaired data for SR tasks. Finally， the paper concludes with a detailed discussion of the challenges and future directions in real-world image super-resolution research. Key challenges include addressing the diverse and unknown degradation patterns encountered in practical applications， improving the efficiency and scalability of SR models for deployment on resource-constrained devices， and enhancing the perceptual quality of reconstructed images. The integration of prior knowledge， such as scene semantics or geometric information， is identified as a promising direction for improving SR performance. Additionally， the paper highlights the potential of emerging techniques such as zero-shot learning， physics-informed models， and hybrid approaches that combine traditional and deep learning-based methods. In summary， this paper provides a thorough analysis of the state of the art in image super-resolution reconstruction， offering valuable insights into the progress， challenges， and future opportunities in the field. By bridging the gap between theory and application， the findings of this paper aim to advance the development of robust SR methods that can address the complexities of real-world scenarios.
Al-Mekhlafi H and Liu S . 2024 . Single image super-resolution： a comprehensive review and recent insight . Frontiers of Computer Science ， 18 （ 1 ）： 181702 ［ DOI： 10.1007/s11704 -023-2588-9 http://dx.doi.org/10.1007/s11704-023-2588-9 ］
Ates H F ， Yildirim S and Gunturk B K . 2023 . Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation . Computer Vision and Image Understanding ， 233 ： 103718 ［ DOI： 10.1016/J.CVIU. 2023.103718 http://dx.doi.org/10.1016/J.CVIU.2023.103718 ］
Bi X P ， Chen S and Zhang L F . 2024 . Blueprint separable convolution Transformer network for lightweight image super-resolution . Journal of Image and Graphics ， 29 （ 4 ）： 875 - 889 .
毕修平 ， 陈实 ， 张乐飞 . 2024 . 轻量级图像超分辨率的蓝图可分离卷积Transformer网络 . 中国图象图形学报 ， 29 （ 4 ）： 875 - 889 ［ DOI： 10.11834/jig.230225 http://dx.doi.org/10.11834/jig.230225 ］
Bevilacqua M ， Roumy A ， Guillemot C and Morel A . 2012 . Low-complexity single image super-resolution based on nonnegative neighbor embedding // Proceedings of the British Machine Vision Conference . Surrey， UK ： 1 - 10 ［ DOI： https：//doi.org/10.5244/C.26.135 http://dx.doi.org/https：//doi.org/10.5244/C.26.135 ］
Belekos S P ， Galatsanos N P ， Babacan S D and Katsaggelos A K . 2009 . Maximum a posteriori super-resolution of compressed video using a new multichannel image prior // Proceedings of the IEEE International Conference on Image Processing . Cairo， Egypt ： 2797 - 2800 . ［ DOI： 10.1109/ICIP.2009.5414174 http://dx.doi.org/10.1109/ICIP.2009.5414174 ］
Bell-Kligler S ， Shocher A and Irani M . 2019 . Blind super-resolution kernel estimation using an internal-gan // Proceedings of the Advances in Neural Information Processing Systems . BC， Canada ： 284 -- 293 ［ DOI： 10.48550/arXiv.1909.06581 http://dx.doi.org/10.48550/arXiv.1909.06581 ］
Bulat A ， Yang J and Tzimiropoulos G . 2018 . To learn image super-resolution， use a gan to learn how to do image degradation first // Proceedings of the European Conference on Computer Vision . Munich， Germany ： 185 - 200 ［DOI： 10.1007/978-3-030-01231-1\_ 12 ］
Chan T M ， Zhang J ， Pu J and Huang H . 2009 . Neighbor embedding based super-resolution algorithm through edge detection and feature selection . Pattern Recognition Letters ， 30 （ 5 ）： 494 - 502 ［ DOI： 10.1016/J.PATREC.2008.11.008 http://dx.doi.org/10.1016/J.PATREC.2008.11.008 ］
Cornillere V ， Djelouah A ， Yifan W ， Hornung O S and Schroers C . 2019 . Blind image super-resolution with spatially variant degradations . ACM Transactions on Graphics ， 38 （ 6 ）： 1 - 13 ［ DOI： 10.1145/3355089.3356575 http://dx.doi.org/10.1145/3355089.3356575 ］
Dong C ， Loy C C ， He K and Tang X . 2015 . Image Super-Resolution Using Deep Convolutional Networks . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 38 （ 2 ）： 295 - 307 ［ DOI： 10.1109/TPAMI.2015.2439281 http://dx.doi.org/10.1109/TPAMI.2015.2439281 ］
Dodgson N A . 1997 . Quadratic interpolation for image resampling . IEEE Transactions on Image Processing ， 6 （ 9 ）： 1322 - 1326 ［ DOI： 10.1109/83.623195 http://dx.doi.org/10.1109/83.623195 ］
Dong W ， Zhang L ， Shi G . 2012 . Nonlocally centralized sparse representation for image restoration . IEEE Transactions on Image Processing ， 22 （ 4 ）： 1620 - 1630 ［ DOI： 10.1109/TIP.2012. 2235847 http://dx.doi.org/10.1109/TIP.2012.2235847 ］
Deng J ， Dong W ， Socher R ， Li L J ， Li K and Li F F . 2009 . ImageNet： A large-scale hierarchical image database // Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Florida， USA ： 248 -- 255 ［ DOI： 10.1109/CVPR.2009.5206848 http://dx.doi.org/10.1109/CVPR.2009.5206848 ］
Dong W ， Zhang L ， Shi G and Wu X . 2011 . Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization . IEEE Transactions on image processing ， 20 （ 7 ）： 1838 - 1857 ［ DOI： 10.1109/TIP.2011. 2108306 http://dx.doi.org/10.1109/TIP.2011.2108306 ］
Dong C ， Loy C C and Tang X . 2016 . Accelerating the super-resolution convolutional neural network // Proceedings of the European Conference on Computer Vision . Amsterdam， The Netherlands ： 391 - 407 ［DOI： 10.1007/978-3-319-46475-6\_ 25 ］
Dai T ， Cai J ， Zhang Y ， Xia S and Zhang L . 2019 . Second-order attention network for single image super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . CA， USA ： 11065 - 11074 ［ DOI： 10.1109/CVPR.2019.01132 http://dx.doi.org/10.1109/CVPR.2019.01132 ］
Everingham M ， Eslami S M A ， Gool L V ， Williams C K I ， Winn J M and Zisserman A . 2015 . The pascal visual object classes challenge： A retrospective . International journal of computer vision ， 111 （ 1 ）： 98 -- 136 ［ DOI： 10.1007/S11263-014-0733-5 http://dx.doi.org/10.1007/S11263-014-0733-5 ］
Fujimoto A ， Ogawa T ， Yamamoto K ， Matsui Y ， Yamasaki T and Aizawa K . 2016 . Manga109 dataset and creation of metadata // Proceedings of the International Workshop on coMics ANalysis， Processing and Understanding . Cancun， Mexico： 2 ：1--2：5 ［ DOI： 10.1145/3011549.3011551 http://dx.doi.org/10.1145/3011549.3011551 ］
Freeman W T ， Jones T R and Pasztor E C . 2002 . Example-based super-resolution . IEEE Computer graphics and Applications ， 22 （ 2 ）： 56 - 65 ［ DOI： 10.1109/38.988747 http://dx.doi.org/10.1109/38.988747 ］
Fritsche M ， Gu S and Timofte R . 2019 . Frequency separation for real-world super-resolution // Proceedings of the IEEE International Conference on Computer Vision Workshop . Seoul， Korea ： 3599 - 3608 ［ DOI： 10.1109/ICCVW.2019.00445 http://dx.doi.org/10.1109/ICCVW.2019.00445 ］
Gu J ， Lu H ， Zuo W and Dong C . 2019 . Blind super-resolution with iterative kernel correction // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . CA， USA ： 1604 - 1613 ［ DOI： 10.1109/CVPR.2019.00170 http://dx.doi.org/10.1109/CVPR.2019.00170 ］
Gao S and Zhuang X . 2023 . Bayesian image super-resolution with deep modeling of image statistics . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 45 （ 2 ）： 1405 - 1423 ［ DOI： 10.1109/TPAMI.2022.3163307 http://dx.doi.org/10.1109/TPAMI.2022.3163307 ］
Huang J B ， Singh A and Ahuja N . 2015 . Single image super-resolution from transformed self-exemplars // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . MA， USA ： 5197 -- 5206 ［ DOI： 10.1109/CVPR. 2015.7299156 http://dx.doi.org/10.1109/CVPR.2015.7299156 ］
Haris M ， Shakhnarovich G and Ukita N . 2018 . Deep back-projection networks for single image super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . UT， USA ： 1664 -- 1673 ［ DOI： 10.1109/CVPR.2018.00179 http://dx.doi.org/10.1109/CVPR.2018.00179 ］
Hung K W and Siu W C . 2012 . Robust soft-decision interpolation using weighted least squares . IEEE Transactions on Image Processing ， 21 （ 3 ）： 1061 - 1069 ［ DOI： 10.1109/TIP.2011.2168416 http://dx.doi.org/10.1109/TIP.2011.2168416 ］
Hu Y ， Gao X ， Li J ， Huang Y and Wang H . 2018 . Single image super-resolution via cascaded multi-scale cross network. arxiv preprint arxiv： 1802.08808 .
He J ， Dong C ， Qiao Y . 2019 . Modulating image restoration with continual levels via adaptive feature modification layers // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . CA， USA ： 11056 - 11064 ［ DOI： 10.1109/ CVPR.2019.01131 http://dx.doi.org/10.1109/CVPR.2019.01131 ］
Jiang J J ， Cheng H ， Li Z Y ， Liu X M and Wang Z Y . 2023 . Deep learning based video-related super-resolution technique： a survey . Journal of Image and Graphics ， 28 （ 7 ）： 1927 - 1964 .
江俊君 ， 程豪 ， 李震宇 ， 刘贤明 ， 王中元 . 2023 . 深度学习视频超分辨率技术综述 . 中国图象图形学报 ， 28 （ 7 ）： 1927 - 1964 ［ DOI： 10.11834/jig.220130 http://dx.doi.org/10.11834/jig.220130 ］
Kim J ， Lee J K amd Lee K M . 2016 . Accurate image super-resolution using very deep convolutional networks // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . NV， USA ： 1646 - 1654 ［ DOI： 10.1109/ CVPR.2016.182 http://dx.doi.org/10.1109/CVPR.2016.182 ］
Kim J ， Lee J K and Lee K M . 2016 . Deeply-recursive convolutional network for image super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . NV， USA ： 1637 - 1645 ［ DOI： 10.1109/CVPR.2016.181 http://dx.doi.org/10.1109/CVPR.2016.181 ］
Kim S Y ， Sim H and Kim M . Koalanet： 2021. Blind super-resolution using kernel-oriented adaptive local adjustment // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Virtual ： 10611 - 10620 ［ DOI： 10.1109/CVPR46437. 2021.01047 http://dx.doi.org/10.1109/CVPR46437.2021.01047 ］
Khan A H ， Micheloni C and Martinel N . 2022 . IDENet： Implicit Degradation Estimation Network for Efficient Blind Super Resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . WA， USA ： 6065 - 6075 ［ DOI： 10.1109/CVPRW63382.2024.00613 http://dx.doi.org/10.1109/CVPRW63382.2024.00613 ］
Khan A H ， Micheloni C and Martinel N . 2024 . Lightweight Prompt Learning Implicit Degradation Estimation Network for Blind Super Resolution . IEEE Transactions on Image Processing ， 33 ： 4556 -- 4567 ［ DOI： 10.1109/TIP.2024.3442613 http://dx.doi.org/10.1109/TIP.2024.3442613 ］
Luo Z ， Huang Y ， Li S ， Wang L and Tan T . 2020 . Unfolding the alternating optimization for blind super resolution // Proceedings of the Advances in Neural Information Processing Systems . Virtual： 5632 - 5643 ［ DOI： 10.48550/arXiv.2010.02631 http://dx.doi.org/10.48550/arXiv.2010.02631 ］
Liu P J ， Zhang H Z ， Cao Y ， Liu S G ， Ren D W and Zuo W M . 2020 . Learning cascaded convolutional networks for blind single image super-resolution . Neurocomputing ， 417 ： 371 - 383 ［ DOI： 10.1016/J.NEUCOM.2020.07.122 http://dx.doi.org/10.1016/J.NEUCOM.2020.07.122 ］
Li Y W ， Zhang K ， Liang J Y ， Cao J Z ， Liu C ， Gong R ， Zhang Y L ， Tang H ， Liu Y ， Demandolx D ， Ranjan R ， Timofte R and Luc V G . 2023 . Lsdir： A large scale dataset for image restoration // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . BC， Canada ： 1775 -- 1787 ［ DOI： 10.1109/CVPRW59228.2023.00178 http://dx.doi.org/10.1109/CVPRW59228.2023.00178 ］
Lin T Y ， Maire M ， Belongie S J ， Hays J ， Perona P ， Ramanan D ， Dollar P and Zitnick C L . 2014 . Microsoft coco： Common objects in context //Proceedings of the European Conference on Computer Vision. Zurich， Switzerland： 740--755 ［DOI： 10.1007/978-3-319-10602-1\_ 48 ］
Ledig C ， Theis L ， Huszar F ， Caballero J ， Cunningham A ， Acosta A ， Aitken A ， Tejani A ， Totz J ， Wang Z H and Shi W Z . 2017 . Photo-realistic single image super-resolution using a generative adversarial network // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . HI， USA ： 4681 - 4690 ［ DOI： 10.1109/CVPR.2017.19 http://dx.doi.org/10.1109/CVPR.2017.19 ］
Lim B ， Son S ， Kim H ， Nah S J and Lee K M . 2017 . Enhanced deep residual networks for single image super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . HI， USA ： 136 - 144 ［ DOI： 10.1109/CVPRW.2017.151 http://dx.doi.org/10.1109/CVPRW.2017.151 ］
Liang J ， Zhang K ， Gu S ， Gool L V and Timofte R . 2021 . Flow-based kernel prior with application to blind super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Virtual ： 10601 - 10610 ［ DOI： 10.1109/ CVPR46437.2021.01046 http://dx.doi.org/10.1109/CVPR46437.2021.01046 ］
Li X and Orchard M T . 2001 . New edge-directed interpolation . IEEE transactions on image processing ， 10 （ 10 ）： 1521 - 1527 ［ DOI： 10.1109/83.951537 http://dx.doi.org/10.1109/83.951537 ］
Li H and Lam K M . 2013 . Guided iterative back-projection scheme for single-image super-resolution // Proceedings of the IEEE Global High Tech Congress on Electronics . Shenzhen， China： 175 - 180 ［ DOI： 10.1109/GHTCE.2013.6767267 http://dx.doi.org/10.1109/GHTCE.2013.6767267 ］
Liang J ， Zeng H and Zhang L . 2022 . Efficient and degradation-adaptive network for real-world image super- resolution // Proceedings of the European Conference on Computer Vision . Tel Aviv， Israel ： 574 - 591 ［DOI： 10.1007/978-3-031-19797-0\_ 33 ］
Liu H ， Shao M ， Qiao Y ， Wan Y and Meng D . 2023 . Unpaired image super-resolution using a lightweight invertible neural network . Pattern Recognition ， 144 ： 109822 ［ DOI： 10.1016/J.PATCOG. 2023.109822 http://dx.doi.org/10.1016/J.PATCOG.2023.109822 ］
Lu L ， Li W ， Tao X ， Lu J and Jia J . 2021 . Masa-sr： Matching acceleration and spatial adaptation for reference-based image super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Virtual ： 6368 - 6377 ［ DOI： 10.1109/CVPR46437.2021.00630 http://dx.doi.org/10.1109/CVPR46437.2021.00630 ］
Martin D R ， Fowlkes C C ， Tal D and Malik J . 2001 . A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics // Proceedings of the International Conference On Computer Vision . British Columbia， Canada ： 416 - 425 ［ DOI： 10.1109/ICCV.2001.937655 http://dx.doi.org/10.1109/ICCV.2001.937655 ］
Mishiba K ， Suzuki T ， Ikehara M . 2010 . Edge-adaptive image interpolation using constrained least squares // Proceedings of the IEEE International Conference on Image Processing . Hong Kong， China ： 2837 - 2840 . ［ DOI： 10.1109/ICIP.2010.5652113 http://dx.doi.org/10.1109/ICIP.2010.5652113 ］
Marquina A ， Osher S J . 2008 . Image super-resolution by TV-regularization and Bregman iteration . Journal of Scientific Computing ， 37 ： 367 - 382 ［ DOI： 10.1007/S10915-008-9214-8 http://dx.doi.org/10.1007/S10915-008-9214-8 ］
Prajapati K ， Chudasama V ， Patel H ， Upla K P ， Raja K B ， Ramachandra R and Busch C . 2021 . Direct unsupervised super-resolution using generative adversarial network （DUS-GAN） for real-world data . IEEE Transactions on Image Processing ， 30 ： 8251 - 8264 ［ DOI： 10.1109/TIP.2021.3113783 http://dx.doi.org/10.1109/TIP.2021.3113783 ］
Romano Y ， Protter M ， Elad M . 2014 . Single image interpolation via adaptive nonlocal sparsity-based modeling . IEEE Transactions on Image Processing ， 23 （ 7 ）： 3085 - 3098 ［ DOI： 10.1109/ TIP.2014.2325774 http://dx.doi.org/10.1109/TIP.2014.2325774 ］
Ren H ， El-Khamy M and Lee J . 2017 . Image super resolution based on fusing multiple convolution neural networks // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . HI， USA ： 54 - 61 ［ DOI： 10.1109/ CVPRW.2017.142 http://dx.doi.org/10.1109/CVPRW.2017.142 ］
Sun W ， Gong D ， Shi Q F ， Anton V D H and Zhang Y N . 2021 . Learning to Zoom-In via Learning to Zoom-Out： Real-World Super- Resolution by Generating and Adapting Degradation . IEEE Transactions on Image Processing . 30 ： 2947 -- 2962 ［ DOI： 10.1109/TIP.2021.3049951 http://dx.doi.org/10.1109/TIP.2021.3049951 ］
Sanchez-Beato A ， Pajares G . 2008 . Noniterative interpolation-based super-resolution minimizing aliasing in the reconstructed image . IEEE Transactions on Image Processing . 17 （ 10 ）： 1817 - 1826 ［ DOI： 10.1109/TIP.2008.2002833 http://dx.doi.org/10.1109/TIP.2008.2002833 ］
Stark H ， Oskoui P . 1989 . High-resolution image recovery from image-plane arrays， using convex projections . JOSA A ， 6 （ 11 ）： 1715 - 1726 ［ DOI： doi.org/10.1364/JOSAA.6.001715 http://dx.doi.org/doi.org/10.1364/JOSAA.6.001715 ］
Schultz R R ， Stevenson R L . 1994 . A Bayesian approach to image expansion for improved definition . IEEE Transactions on Image Processing ， 3 （ 3 ）： 233 - 242 ［ DOI： 10.1109/83.287017 http://dx.doi.org/10.1109/83.287017 ］
Schulter S ， Leistner C and Bischof H . 2015 . Fast and accurate image upscaling with super-resolution forests // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . MA， USA ： 3791 - 3799 ［ DOI： 10.1109/CVPR.2015.7299003 http://dx.doi.org/10.1109/CVPR.2015.7299003 ］
Shao K ， Fan Q ， Zhang Y ， Bao F and Zhang C . 2021 . Noisy single image super-resolution based on local fractal feature analysis . IEEE Access ， 9 ： 33385 - 33395 ［ DOI： 10.1109/ACCESS.2021. 3061118 http://dx.doi.org/10.1109/ACCESS.2021.3061118 ］
Shen H ， Li P ， Zhang L and Zhao Y . 2004 . A MAP algorithm to super-resolution image reconstruction // Proceedings of the International Conference on Image and Graphics . Hong Kong， China ： 544 - 547 ［ DOI： 10.1109/ICIG.2004.8 http://dx.doi.org/10.1109/ICIG.2004.8 ］
Sun J ， Xu Z and Shum H Y . 2008 . Image super-resolution using gradient profile prior // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Alaska， USA ： 1 - 8 ［ DOI： 10.1109/CVPR.2008.4587659 http://dx.doi.org/10.1109/CVPR.2008.4587659 ］
Thurnhofer S ， Mitra S K . 1996 . Edge-enhanced image zooming . Optical Engineering . 35 （ 7 ）： 1862 - 1870 ［ DOI： doi.org/10.1117/ 1.600619 http://dx.doi.org/doi.org/10.1117/1.600619 ］
Tang Z ， Deng M ， Xiao C and Yu J . 2011 . Projection onto convex sets super-resolution image reconstruction based on wavelet bi-cubic interpolation // Proceedings of International Conference on Electronic & Mechanical Engineering and Information Technology . Harbin， China ： 351 - 354 ［ DOI： 10.1109/EMEIT. 2011.6022950 http://dx.doi.org/10.1109/EMEIT.2011.6022950 ］
Tai Y ， Yang J and Liu X . 2017 . Image super-resolution via deep recursive residual network // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . HI， USA ： 3147 - 3155 ［ DOI： 10.1109/CVPR.2017.298 http://dx.doi.org/10.1109/CVPR.2017.298 ］
Ulyanov D ， Vedaldi A and Lempitsky V S . 2018 . Deep image prior // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . UT， USA ： 9446 - 9454 ［ DOI： 10.1109/ CVPR.2018.00984 http://dx.doi.org/10.1109/CVPR.2018.00984 ］
Wang X T ， Xie L B ， Dong C and Shan Y . 2021 . Real-ESRGAN： Training real-world blind super-resolution with pure synthetic data // Proceedings of the IEEE International Conference on Computer Vision Workshops . BC， Canada ： 1905--1914 ［ DOI： 10.1109/ICCVW54120.2021.00217 http://dx.doi.org/10.1109/ICCVW54120.2021.00217 ］
Wei P X ， Xie Z W ， Lu H N ， Ye Q X ， Zuo W M and Lin L . 2020 . Component Divide-and-Conquer for Real-World Image Super-Resolution //Proceedings of the European Conference on Computer Vision. Glasgow， UK： 101--117 ［DOI： 10.1007/ 978-3-030-58598-3\_ 7 ］
Wang L ， Wang Y ， Dong X ， Xu Q ， Yang J ， An W and Guo Y . 2021 . Unsupervised degradation representation learning for blind super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Virtual ： 10581 - 10590 ［ DOI： 10.1109/CVPR46437.2021.01044 http://dx.doi.org/10.1109/CVPR46437.2021.01044 ］
Wang Y ， Ming J ， Jia X ， Elder J H and Lu H . 2022 . Blind image super-resolution with degradation-aware adaptation // Proceedings of the Asian Conference on Computer Vision . Macao， China ： 894 - 910 ［DOI： 10.1007/978-3-031-26313-2\_ 5 ］
Xu Z ， Ma Q and Yuan F . 2020 . Single color image super-resolution using sparse representation and color constraint . Journal of Systems Engineering and Electronics ， 31 （ 2 ）： 266 - 271 ［ DOI： 10.23919/JSEE.2020.000004 http://dx.doi.org/10.23919/JSEE.2020.000004 ］
Xia B ， Zhang Y ， Wang Y ， Tian Y ， Yang W ， Timofte R and Gool L V . 2023 . Knowledge distillation based degradation estimation for blind super-resolution // Proceedings of the International Conference on Learning Representations . Kigali， Rwanda ［ DOI： 10.48550/arXiv.2211.16928 http://dx.doi.org/10.48550/arXiv.2211.16928 ］
Xia J ， Yang Z ， Li S ， Zhang S ， Fu Y and Gunduz D . 2024 . Blind Super-Resolution Via Meta-Learning and Markov Chain Monte Carlo Simulation . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 1 - 18 ［ DOI： 10.1109/TPAMI.2024. 3400041 http://dx.doi.org/10.1109/TPAMI.2024.3400041 ］
Yuan Y ， Liu S Y ， Zhang J W ， Dong C and Lin L . 2018 . Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . UT， USA ： 701 - 710 ［ DOI： 10.1109/CVPRW.2018.00113 http://dx.doi.org/10.1109/CVPRW.2018.00113 ］
Yoo J S and Kim J O . 2019 . Noise-robust iterative back-projection . IEEE Transactions on Image Processing ， 29 ： 1219 - 1232 ［ DOI： 10.1109/TIP.2019.2940414 http://dx.doi.org/10.1109/TIP.2019.2940414 ］
Yamawaki K ， Sun Y and Han X H . 2021 . Blind image super resolution using deep unsupervised learning . Electronics ， 10 （ 21 ）： 2591 ［ DOI： doi.org/10.3390/electronics10212591 http://dx.doi.org/doi.org/10.3390/electronics10212591 ］
Yin P ， Liu Z ， Wu D ， Huo H ， Wang H and Zhang K . 2022 . Unsupervised simple Siamese representation learning for blind super-resolution . Engineering Applications of Artificial Intelligence ， 114 ： 105092 ［ DOI： 10.1016/J.ENGAPPAI.2022. 105092 http://dx.doi.org/10.1016/J.ENGAPPAI.2022.105092 ］
Yang Z ， Xia J ， Li S ， Liu W ， Zhi S ， Zhang S ， Liu L ， Fu Y and Gunduz D . 2024 . Meta-learning based bind image super-resolution approach to different degradations . Neural Networks ， 178 ： 106429 ［ DOI： doi.org/10.1016/j.neunet.2024.106429 http://dx.doi.org/doi.org/10.1016/j.neunet.2024.106429 ］
Yan Q ， Niu A ， Wang C ， Dong W ， Wozniak M and Zhang Y . 2024 . KGSR： A kernel guided network for real-world blind super-resolution . Pattern Recognition ， 147 ： 110095 ［ DOI： 10.1016/J.PATCOG.2023.110095 http://dx.doi.org/10.1016/J.PATCOG.2023.110095 ］
Yuan Y ， Liu S ， Zhang J ， Zhang Y ， Dong C and Lin L . 2018 . Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . UT， USA ： 701 - 710 ［ DOI： 10.1109/CVPRW. 2018.00113 http://dx.doi.org/10.1109/CVPRW.2018.00113 ］
Zhang K ， Zuo W and Zhang L . 2019 . Deep plug-and-play super-resolution for arbitrary blur kernels // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . CA， USA ： 1671 - 1681 ［ DOI： 10.1109/CVPR.2019. 00177 http://dx.doi.org/10.1109/CVPR.2019.00177 ］
Zhang R ， Isola P ， Efros A ， Shechtman E and Wang O . 2018 . The unreasonable effectiveness of deep features as a perceptual metric // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . UT， USA ： 586 -- 595 ［ DOI： 10.1109/CVPR.2018.00068 http://dx.doi.org/10.1109/CVPR.2018.00068 ］
Zhang Y ， Li K ， Li K ， Wang L ， Zhong B and Fu Y . 2018 . Image super-resolution using very deep residual channel attention networks // Proceedings of the European Conference on Computer Vision . Munich， Germany ： 286 - 301 ［DOI： 10.1007/978-3-030-01234-2\_ 18 ］
Zhang Y ， Fan Q ， Bao F ， Liu Y and Zhang C . 2018 . Single-image super-resolution based on rational fractal interpolation . IEEE Transactions on Image Processing ， 27 （ 8 ）： 3782 - 3797 ［ DOI： 10.1109/TIP.2018.2826139 http://dx.doi.org/10.1109/TIP.2018.2826139 ］
Zhang K ， Gao X ， Tao D ， Li X . 2012 . Single image super-resolution with non-local means and steering kernel regression . IEEE Transactions on Image Processing ， 21 （ 11 ）： 4544 - 4556 ［ DOI： 10.1109/TIP.2012.2208977 http://dx.doi.org/10.1109/TIP.2012.2208977 ］
Zhang K ， Zuo W a nd Zhang L . 2018 . Learning a single convolutional super-resolution network for multiple degradations // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . UT， USA ： 3262 - 3271 ［ DOI： 10.1109/CVPR.2018.00344 http://dx.doi.org/10.1109/CVPR.2018.00344 ］
Zhang K ， Zuo W and Zhang L . 2019 . Deep plug-and-play super-resolution for arbitrary blur kernels // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . CA， USA ： 1671 - 1681 ［ DOI： 10.1109/CVPR.2019.00177 http://dx.doi.org/10.1109/CVPR.2019.00177 ］
Zhang K ， Gool L V and Timofte R . 2020 . Deep unfolding network for image super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . WA， USA ： 3217 - 3226 ［ DOI： 10.1109/CVPR42600.2020.00328 http://dx.doi.org/10.1109/CVPR42600.2020.00328 ］
Zhou Y ， Deng W ， Tong T and Gao Q . 2020 . Guided frequency separation network for real-world super-resolution // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . WA， USA ： 428 - 429 ［ DOI： 10.1109/CVPRW50498. 2020.00222 http://dx.doi.org/10.1109/CVPRW50498.2020.00222 ］
相关文章
相关作者
相关机构
京公网安备11010802024621