Abstract
Single-image super-resolution (SISR) is an important task in image processing, which aims to enhance the resolution of imaging systems. Recently, SISR has made a huge leap and has achieved promising results with the help of deep learning (DL). In this survey, we give an overview of DL-based SISR methods and group them according to their design targets. Specifically, we first introduce the problem definition, research background, and the significance of SISR. Secondly, we introduce some related works, including benchmark datasets, upsampling methods, optimization objectives, and image quality assessment methods. Thirdly, we provide a detailed investigation of SISR and give some domain-specific applications of it. Fourthly, we present the reconstruction results of some classic SISR methods to intuitively know their performance. Finally, we discuss some issues that still exist in SISR and summarize some new trends and future directions. This is an exhaustive survey of SISR, which can help researchers better understand SISR and inspire more exciting research in this field. An investigation project for SISR is provided at https://github.com/CV-JunchengLi/SISR-Survey.
- [1] Romero Adriana, Ballas Nicolas, K. Samira Ebrahimi, Chassang Antoine, Gatta Carlo, and Bengio Yoshua. 2015. Fitnets: Hints for thin deep nets. In ICLR.Google Scholar
- [2] . 2017. NTIRE 2017 challenge on single image super-resolution: Dataset and study. In CVPRW.Google ScholarCross Ref
- [3] . 2018. Fast, accurate, and lightweight super-resolution with cascading residual network. In ECCV.Google ScholarDigital Library
- [4] . 2018. Image super-resolution via progressive cascading residual network. In CVPRW.Google ScholarCross Ref
- [5] . 2019. Variational information distillation for knowledge transfer. In CVPR.Google ScholarCross Ref
- [6] . 2020. A deep journey into super-resolution: A survey. Computing Surveys 53, 3 (2020), 1–34.Google ScholarDigital Library
- [7] . 2010. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 5 (2010), 898–916.Google ScholarDigital Library
- [8] . 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In BMVC.Google ScholarCross Ref
- [9] . 2018. The 2018 PIRM challenge on perceptual image super-resolution. In ECCVW.Google Scholar
- [10] . 2018. The perception-distortion tradeoff. In CVPR.Google ScholarCross Ref
- [11] . 2018. To learn image super-resolution, use a GAN to learn how to do image degradation first. In ECCV.Google ScholarDigital Library
- [12] . 2019. Toward real-world single image super-resolution: A new benchmark and a new model. In ICCV.Google ScholarCross Ref
- [13] . 2022. MST++: Multi-stage spectral-wise transformer for efficient spectral reconstruction. In CVPR.Google ScholarCross Ref
- [14] Chunshui Cao, Xianming Liu, Yi Yang, Yinan Yu, Jiang Wang, Zilei Wang, Yongzhen Huang, Liang Wang, Chang Huang, Wei Xu, Deva Ramanan, and Thomas S. Huang. 2015. Look and think twice: Capturing top-down visual attention with feedback convolutional neural networks. In ICCV.Google Scholar
- [15] . 2019. Single image super-resolution via multi-scale residual channel attention network. Neurocomputing 358 (2019), 424–436. https://www.sciencedirect.com/science/article/abs/pii/S0925231219307726Google ScholarDigital Library
- [16] . 2016. Human pose estimation with iterative error feedback. In CVPR.Google ScholarCross Ref
- [17] . 2019. Multi-scale dense network for single-image super-resolution. In ICASSP.Google ScholarCross Ref
- [18] . 2004. Super-resolution through neighbor embedding. In CVPR.Google ScholarCross Ref
- [19] . 2022. Real-world blind super-resolution via feature matching with implicit high-resolution priors. In ACMMM.Google ScholarDigital Library
- [20] . 2019. Camera lens super-resolution. In CVPR.Google ScholarCross Ref
- [21] . 2022. Real-world single image super-resolution: A brief review. Information Fusion 79 (2022), 124–145. https://www.sciencedirect.com/science/article/abs/pii/S1566253521001792Google ScholarDigital Library
- [22] . 2021. Pre-trained image processing transformer. In CVPR.Google ScholarCross Ref
- [23] . 2022. Simple baselines for image restoration. In CECCV.Google ScholarDigital Library
- [24] Xiangyu Chen, Xintao Wang, Jiantao Zhou, Yu Qiao, and Chao Dong. 2023. Activating more pixels in image super-resolution transformer. In CVPR.Google Scholar
- [25] . 2018. Efficient and accurate MRI super-resolution using a generative adversarial network and 3D multi-level densely connected network. In MICCAI.Google ScholarDigital Library
- [26] . 2023. Dual aggregation transformer for image super-resolution. In ICCV.Google ScholarCross Ref
- [27] Zheng Chen, Yulun Zhang, Jinjin Gu, yongbing zhang, Linghe Kong, and Xin Yuan. 2022. Cross aggregation transformer for image restoration. In NeurIPS.Google Scholar
- [28] . 2023. N-gram in swin transformers for efficient lightweight image super-resolution. In CVPR.Google ScholarCross Ref
- [29] . 2017. Xception: Deep learning with depthwise separable convolutions. In CVPR.Google ScholarCross Ref
- [30] . 2022. NAFSSR: Stereo image super-resolution using NAFNet. In CVPR.Google ScholarCross Ref
- [31] . 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. In ICML.Google ScholarDigital Library
- [32] . 2021. Feedback network for mutually boosted stereo image super-resolution and disparity estimation. In ACMMM.Google Scholar
- [33] . 2019. Second-order attention network for single image super-resolution. In CVPR.Google ScholarCross Ref
- [34] . 2009. ImageNet: A large-scale hierarchical image database. In CVPR.Google ScholarCross Ref
- [35] . 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. Retrieved from https://arxiv.org/abs/1810.04805Google Scholar
- [36] . 2020. Image quality assessment: Unifying structure and texture similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 5 (2020), 2567–2581.Google Scholar
- [37] . 2019. Exemplar guided face image super-resolution without facial landmarks. In CVPRW.Google ScholarCross Ref
- [38] . 2014. Learning a deep convolutional network for image super-resolution. In ECCV.Google ScholarCross Ref
- [39] . 2016. Accelerating the super-resolution convolutional neural network. In ECCV.Google ScholarCross Ref
- [40] . 2011. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Transactions on Image Processing 20, 7 (2011), 1838–1857.Google ScholarDigital Library
- [41] . 2020. Remote sensing image super-resolution using second-order multi-scale networks. IEEE Transactions on Geoscience and Remote Sensing 59, 4 (2020), 3473–3485.Google ScholarCross Ref
- [42] . 1979. Lanczos filtering in one and two dimensions. Journal of Applied Meteorology and Climatology 18, 8 (1979), 1016–1022.Google ScholarCross Ref
- [43] . 2020. Soft-edge assisted network for single image super-resolution. IEEE Transactions on Image Processing 29 (2020), 4656–4668. https://ieeexplore.ieee.org/abstract/document/9007623Google ScholarDigital Library
- [44] . 2021. Task transformer network for joint MRI reconstruction and super-resolution. In MICCAI.Google ScholarDigital Library
- [45] . 2019. Hyperspectral image super-resolution with optimized RGB guidance. In CVPR.Google ScholarCross Ref
- [46] . 2016. Manga109 dataset and creation of metadata. In MANPU.Google ScholarDigital Library
- [47] . 2021. Fourier space losses for efficient perceptual image super-resolution. In ICCV.Google ScholarCross Ref
- [48] . 2022. Feature distillation interaction weighting network for lightweight image super-resolution. In AAAI.Google ScholarCross Ref
- [49] . 2023. JDSR-GAN: Constructing an efficient joint learning network for masked face super-resolution. IEEE Transactions on Multimedia 25 (2023), 1505–1512. https://ieeexplore.ieee.org/abstract/document/10032643Google ScholarDigital Library
- [50] . 2022. Lightweight bimodal network for single-image super-resolution via symmetric CNN and recursive transformer. In IJCAI.Google Scholar
- [51] . 2018. Image super-resolution using knowledge distillation. In ACCV.Google Scholar
- [52] Sicheng Gao, Xuhui Liu, Bohan Zeng, Sheng Xu, Yanjing Li, Xiaoyan Luo, Jianzhuang Liu, Xiantong Zhen, and Baochang Zhang. 2023. Implicit diffusion models for continuous super-resolution. In CVPR.Google Scholar
- [53] . 2015. Texture synthesis using convolutional neural networks. In NeurIPS.Google Scholar
- [54] . 2015. A neural algorithm of artistic style. arXiv:1508.06576. Retrieved from https://arxiv.org/abs/1508.06576Google Scholar
- [55] . 2023. Multimodal multi-head convolutional attention with various kernel sizes for medical image super-resolution. In CVPR.Google ScholarCross Ref
- [56] . 2014. Generative adversarial nets. In NeurIPS.Google Scholar
- [57] . 2019. Blind super-resolution with iterative kernel correction. In CVPR.Google ScholarCross Ref
- [58] . 2019. Deep residual squeeze and excitation network for remote sensing image super-resolution. Remote Sensing 11, 15 (2019), 1817.Google ScholarCross Ref
- [59] . 2022. VQFR: Blind face restoration with vector-quantized dictionary and parallel decoder. In ECCV.Google ScholarDigital Library
- [60] . 2020. Closed-loop matters: Dual regression networks for single image super-resolution. In CVPR.Google ScholarCross Ref
- [61] . 2018. Image super-resolution via dual-state recurrent networks. In CVPR.Google ScholarCross Ref
- [62] . 2020. Deep back-projectinetworks for single image super-resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 12 (2020), 4323–4337.Google ScholarDigital Library
- [63] . 2018. A new deep generative network for unsupervised remote sensing single-image super-resolution. IEEE Transactions on Geoscience and Remote sensing 56, 11 (2018), 6792–6810.Google ScholarCross Ref
- [64] . 2015. Convolutional neural networks at constrained time cost. In CVPR.Google ScholarCross Ref
- [65] . 2016. Deep residual learning for image recognition. In CVPR.Google ScholarCross Ref
- [66] . 2017. GANs trained by a two time-scale update rule converge to a local nash equilibrium. In NeurIPS.Google Scholar
- [67] . 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https://arxiv.org/abs/1503.02531Google Scholar
- [68] . 2020. Denoising diffusion probabilistic models. In NeurIPS.Google Scholar
- [69] . 2018. Squeeze-and-excitation networks. In CVPR.Google ScholarCross Ref
- [70] . 2019. Meta-SR: A magnification-arbitrary network for super-resolution. In CVPR.Google ScholarCross Ref
- [71] . 2020. Meta-USR: A unified super-resolution network for multiple degradation parameters. IEEE Transactions on Neural Networks and Learning Systems 32, 9 (2020), 4151–4165.Google ScholarCross Ref
- [72] . 2017. Densely connected convolutional networks. In CVPR.Google ScholarCross Ref
- [73] . 2015. Single image super-resolution from transformed self-exemplars. In CVPR.Google ScholarCross Ref
- [74] . 2019. Lightweight image super-resolution with information multi-distillation network. In ACMMM.Google ScholarDigital Library
- [75] . 2018. Fast and accurate single image super-resolution via information distillation network. In CVPR.Google ScholarCross Ref
- [76] . 2018. Enhancing the spatial resolution of stereo images using a parallax prior. In CVPR.Google ScholarCross Ref
- [77] . 2008. Image super-resolution using gradient profile prior. In CVPR.Google Scholar
- [78] . 2020. Learning spatial-spectral prior for super-resolution of hyperspectral imagery. IEEE Transactions on Computational Imaging 6 (2020), 1082–1096. https://ieeexplore.ieee.org/abstract/document/9097432Google ScholarCross Ref
- [79] . 2020. PIPAL: A large-scale image quality assessment dataset for perceptual image restoration. In ECCV.Google ScholarDigital Library
- [80] . 2016. Perceptual losses for real-time style transfer and super-resolution. In ECCV.Google ScholarCross Ref
- [81] . 2018. The relativistic discriminator: A key element missing from standard GAN. arXiv:1807.00734. Retrieved from https://arxiv.org/abs/1807.00734Google Scholar
- [82] . 2019. A style-based generator architecture for generative adversarial networks. In CVPR.Google ScholarCross Ref
- [83] . 2016. Accurate image super-resolution using very deep convolutional networks. In CVPR.Google ScholarCross Ref
- [84] . 2016. Deeply-recursive convolutional network for image super-resolution. In CVPR.Google ScholarCross Ref
- [85] . 2010. Single-image super-resolution using sparse regression and natural image prior. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 6 (2010), 1127–1133.Google ScholarDigital Library
- [86] . 2012. ImageNet classification with deep convolutional neural networks. In NeurIPS.Google Scholar
- [87] . 2017. Deep Laplacian pyramid networks for fast and accurate super-resolution. In CVPR.Google ScholarCross Ref
- [88] . 2017. Deep Laplacian pyramid networks for fast and accurate super-resolution. In CVPR.Google ScholarCross Ref
- [89] . 2020. MADNet: A fast and lightweight network for single-image super resolution. IEEE Transactions on Cybernetics 51, 3 (2020), 1443–1453.Google ScholarCross Ref
- [90] . 2015. Deep learning. Nature 521, 7553 (2015), 436–444.Google ScholarCross Ref
- [91] Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. 2017. Photo-realistic single image super-resolution using a generative adversarial network. In CVPR.Google Scholar
- [92] . 2020. MaskGAN: Towards diverse and interactive facial image manipulation. In CVPR.Google ScholarCross Ref
- [93] . 2020. Learning with privileged information for efficient image super-resolution. In ECCV.Google ScholarDigital Library
- [94] . 2021. Hybrid-scale self-similarity exploitation for remote sensing image super-resolution. IEEE Transactions on Geoscience and Remote Sensing 60 (2021), 1–10. https://ieeexplore.ieee.org/abstract/document/9400474Google Scholar
- [95] . 2020. PAMS: Quantized super-resolution via parameterized max scale. In ECCV.Google ScholarDigital Library
- [96] . 2022. SRDiff: Single image super-resolution with diffusion probabilistic models. Neurocomputing 479 (2022), 47–59. https://www.sciencedirect.com/science/article/pii/S0925231222000522Google ScholarDigital Library
- [97] . 2020. MDCN: Multi-scale dense cross network for image super-resolution. IEEE Transactions on Circuits and Systems for Video Technology 31, 7 (2020), 2547–2561.Google ScholarCross Ref
- [98] . 2018. Multi-scale residual network for image super-resolution. In ECCV.Google ScholarDigital Library
- [99] . 2019. Lightweight and accurate recursive fractal network for image super-resolution. In ICCVW.Google ScholarCross Ref
- [100] . 2023. Lightweight image super-resolution with pyramid clustering transformer. IEEE Transactions on Circuits and Systems for Video Technology (2023). https://ieeexplore.ieee.org/abstract/document/10185933Google Scholar
- [101] . 2023. Cross-receptive focused inference network for lightweight image super-resolution. IEEE Transactions on Multimedia 26 (2023), 864–877. https://ieeexplore.ieee.org/abstract/document/10114600Google ScholarDigital Library
- [102] . 2023. DLGSANet: Lightweight dynamic local and global self-attention networks for image super-resolution. In ICCV.Google ScholarCross Ref
- [103] . 2023. Efficient and explicit modelling of image hierarchies for image restoration. In CVPR.Google ScholarCross Ref
- [104] . 2018. Single hyperspectral image super-resolution with grouped deep recursive residual network. In BigMM.Google ScholarCross Ref
- [105] . 2022. Blueprint separable residual network for efficient image super-resolution. In CVPR.Google ScholarCross Ref
- [106] . 2019. Feedback network for image super-resolution. In CVPR.Google ScholarCross Ref
- [107] . 2021. SwinIR: Image restoration using swin transformer. In ICCVW.Google ScholarCross Ref
- [108] . 2017. Enhanced deep residual networks for single image super-resolution. In CVPRW.Google ScholarCross Ref
- [109] . 2023. Memory-friendly scalable super-resolution via rewinding lottery ticket hypothesis. In CVPR.Google ScholarCross Ref
- [110] . 2023. DiffBIR: Towards blind image restoration with generative diffusion prior. arXiv:2308.15070. Retrieved from https://arxiv.org/abs/2308.15070Google Scholar
- [111] . 2022. Blind image super-resolution: A survey and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 5 (2022), 5461–5480.Google Scholar
- [112] . 2021. A spectral grouping and attention-driven residual dense network for hyperspectral image super-resolution. IEEE Transactions on Geoscience and Remote Sensing 59, 9 (2021), 7711–7725.Google ScholarCross Ref
- [113] . 2018. Non-local recurrent network for image restoration. In NeurIPS.Google Scholar
- [114] . 2020. Residual feature distillation network for lightweight image super-resolution. In ECCVW.Google ScholarDigital Library
- [115] . 2020. Residual feature aggregation network for image super-resolution. In CVPR.Google ScholarCross Ref
- [116] . 2022. Dual learning-based graph neural network for remote sensing image super-resolution. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1–14. https://ieeexplore.ieee.org/abstract/document/9861602Google Scholar
- [117] . 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In CVPR.Google Scholar
- [118] . 2015. Deep learning face attributes in the wild. In ICCV.Google ScholarDigital Library
- [119] . 2021. Transformer for single image super-resolution. In CVPRW.Google Scholar
- [120] . 2024. AdaFormer: Efficient transformer with adaptive token sparsification for image super-resolution. In AAAI.Google ScholarCross Ref
- [121] . 2022. Adjustable memory-efficient image super-resolution via individual kernel sparsity. In ACMMM.Google ScholarDigital Library
- [122] . 2021. Boosting lightweight single image super-resolution via joint-distillation. In ACMMM.Google ScholarDigital Library
- [123] . 2022. Lattice network for lightweight image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4826–4842.Google Scholar
- [124] . 2020. Unfolding the alternating optimization for blind super resolution. In NeurIPS.Google Scholar
- [125] . 2020. Structure-preserving super resolution with gradient guidance. In CVPR.Google ScholarCross Ref
- [126] . 2017. Learning a no-reference quality metric for single-image super-resolution. Computer Vision and Image Understanding 158 (2017), 1–16. https://www.sciencedirect.com/science/article/pii/S107731421630203XGoogle ScholarDigital Library
- [127] . 2016. Waterloo exploration database: New challenges for image quality assessment models. IEEE Transactions on Image Processing 26, 2 (2016), 1004–1016.Google ScholarDigital Library
- [128] . 2019. Efficient super resolution using binarized neural network. In CVPRW.Google ScholarCross Ref
- [129] . 2020. Unpaired image super-resolution using pseudo-supervision. In CVPR.Google ScholarCross Ref
- [130] . 2001. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In ICCV.Google ScholarCross Ref
- [131] . 2019. Deep residual refining based pseudo-multi-frame network for effective single image super-resolution. IET Image Processing 13, 4 (2019), 591–599.Google ScholarCross Ref
- [132] . 2018. An effective single-image super-resolution model using squeeze-and-excitation networks. In NeurIPS.Google ScholarDigital Library
- [133] . 2017. Hyperspectral image spatial super-resolution via 3D full convolutional neural network. Remote Sensing 9, 11 (2017), 1139.Google ScholarCross Ref
- [134] . 2020. Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining. In CVPR.Google ScholarCross Ref
- [135] . 2012. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing 21, 12 (2012), 4695–4708.Google ScholarDigital Library
- [136] . 2012. Making a “completely blind” image quality analyzer. IEEE Signal Processing Letters 20, 3 (2012), 209–212.Google ScholarCross Ref
- [137] . 2020. Multi-attention based ultra lightweight image super-resolution. In ECCV.Google ScholarDigital Library
- [138] . 2020. Single image super-resolution via a holistic attention network. In ECCV.Google Scholar
- [139] . 2018. SRFeat: Single image super-resolution with feature discrimination. In ECCV.Google ScholarDigital Library
- [140] . 2020. SAINT: Spatially aware interpolation network for medical slice synthesis. In CVPR.Google ScholarCross Ref
- [141] . 2020. Multi-scale feature fusion residual network for Single Image Super-Resolution. Neurocomputing 379 (2020), 334–342. https://www.sciencedirect.com/science/article/pii/S0925231219315140Google ScholarDigital Library
- [142] . 2019. SROBB: Targeted perceptual loss for single image super-resolution. In ICCV.Google ScholarCross Ref
- [143] . 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434. Retrieved from https://arxiv.org/abs/1511.06434Google Scholar
- [144] . 2019. Language models are unsupervised multitask learners. OpenAI Blog (2019).Google Scholar
- [145] . 1993. HYDICE: An airborne system for hyperspectral imaging. In Imaging Spectrometry of the Terrestrial Environment. SPIE Digital Library. 173–179. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/1937/1/HYDICE-an-airborne-system-for-hyperspectral-imaging/10.1117/12.157055.short#_=_Google ScholarCross Ref
- [146] . 2022. High-resolution image synthesis with latent diffusion models. In CVPR.Google ScholarCross Ref
- [147] . 2022. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4713–4726.Google Scholar
- [148] . 2019. SinGAN: Learning a generative model from a single natural image. In ICCV.Google ScholarCross Ref
- [149] Shuyao Shang, Zhengyang Shan, Guangxing Liu, and Jinglin Zhang. 2023. ResDiff: Combining CNN and diffusion model for image super-resolution. In AAAI.Google Scholar
- [150] . 2019. Multipath feedforward network for single image super-resolution. Multimedia Tools and Applications 78 (2019), 19621–19640. https://link.springer.com/article/10.1007/s11042-019-7334-9#citeasGoogle ScholarDigital Library
- [151] . 2016. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In CVPR.Google ScholarCross Ref
- [152] . 2018. “zero-shot” super-resolution using deep internal learning. In CVPR.Google Scholar
- [153] . 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Retrieved from https://arxiv.org/abs/1409.1556Google Scholar
- [154] Bin Sun, Yulun Zhang, Songyao Jiang, and Yun Fu. 2023. Hybrid pixel-unshuffled network for lightweight image super-resolution. In AAAI.Google Scholar
- [155] Long Sun, Jinshan Pan, and Jinhui Tang. 2022. Shufflemixer: An efficient convnet for image super-resolution. In NeurIPS.Google Scholar
- [156] . 2017. Inception-v4, inception-ResNet and the impact of residual connections on learning. In AAAI.Google ScholarCross Ref
- [157] . 2016. Rethinking the inception architecture for computer vision. In CVPR.Google ScholarCross Ref
- [158] . 2017. Image super-resolution via deep recursive residual network. In CVPR.Google ScholarCross Ref
- [159] . 2017. MemNet: A persistent memory network for image restoration. In CVPR.Google ScholarCross Ref
- [160] . 2017. NTIRE 2017 challenge on single image super-resolution: Methods and results. In CVPRW.Google ScholarCross Ref
- [161] . 2016. Seven ways to improve example-based single image super resolution. In CVPR.Google ScholarCross Ref
- [162] . 2017. Image super-resolution using dense skip connections. In ICCV.Google ScholarCross Ref
- [163] . 2023. Light field image super-resolution network via joint spatial-angular and epipolar information. IEEE Transactions on Computational Imaging 9 (2023), 350–366. https://ieeexplore.ieee.org/abstract/document/10081009Google ScholarCross Ref
- [164] . 2017. Attention is all you need. In NeurIPS.Google ScholarDigital Library
- [165] . 2019. Lightweight image super-resolution with adaptive weighted learning network. arXiv:1904.02358. Retrieved from https://arxiv.org/abs/1904.02358Google Scholar
- [166] . 2023. Omni aggregation networks for lightweight image super-resolution. In CVPR.Google ScholarCross Ref
- [167] . 2023. Exploiting diffusion prior for real-world image super-resolution. arXiv:2305.07015. Retrieved from https://arxiv.org/abs/2305.07015Google Scholar
- [168] . 2021. Exploring sparsity in image super-resolution for efficient inference. In CVPR.Google ScholarCross Ref
- [169] Longguang Wang, Yulan Guo, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, and Wei An. 2020. Parallax attention for unsupervised stereo correspondence learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 4 (202), 2108–2125.Google Scholar
- [170] . 2020. Dual super-resolution learning for semantic segmentation. In CVPR.Google ScholarCross Ref
- [171] . 2021. Unsupervised degradation representation learning for blind super-resolution. In CVPR.Google ScholarCross Ref
- [172] . 2019. Learning parallax attention for stereo image super-resolution. In CVPR.Google ScholarCross Ref
- [173] Longguang Wang, Yingqian Wang, Zaiping Lin, Jungang Yang, Wei An, and Yulan Guo. 2021. Learning a single network for scale-arbitrary super-resolution. In CVPR.Google Scholar
- [174] . 2018. Non-local neural networks. In CVPR.Google ScholarCross Ref
- [175] . 2021. Towards real-world blind face restoration with generative facial prior. In CVPR.Google ScholarCross Ref
- [176] . 2018. Recovering realistic texture in image super-resolution by deep spatial feature transform. In CVPR.Google ScholarCross Ref
- [177] . 2018. ESRGAN: Enhanced super-resolution generative adversarial networks. In ECCV.Google Scholar
- [178] . 2023. High-resolution GAN inversion for degraded images in large diverse datasets. In AAAI.Google Scholar
- [179] . 2018. LFNet: A novel bidirectional recurrent convolutional neural network for light-field image super-resolution. IEEE Transactions on Image Processing 27, 9 (2018), 4274–4286.Google ScholarCross Ref
- [180] . 2018. A fully progressive approach to single-image super-resolution. In CVPRW.Google ScholarCross Ref
- [181] . 2023. Remote sensing image super-resolution via multiscale enhancement network. IEEE Geoscience and Remote Sensing Letters 20 (2023), 1–5. https://ieeexplore.ieee.org/abstract/document/10050509Google Scholar
- [182] . 2019. CT-image of rock samples super resolution using 3D convolutional neural network. Computers & Geosciences 133 (2019), 104314. https://www.sciencedirect.com/science/article/pii/S0098300418310562Google ScholarCross Ref
- [183] . 2022. Disentangling light fields for super-resolution and disparity estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 1 (2022), 425–443.Google ScholarCross Ref
- [184] . 2019. Flickr1024: A large-scale dataset for stereo image super-resolution. In ICCVW.Google ScholarCross Ref
- [185] . 2020. Spatial-angular interaction for light field image super-resolution. In ECCV.Google ScholarDigital Library
- [186] . 2020. Light field image super-resolution using deformable convolution. IEEE Transactions on Image Processing 30 (2020), 1057–1071. https://ieeexplore.ieee.org/abstract/document/9286855Google ScholarCross Ref
- [187] . 2021. Symmetric parallax attention for stereo image super-resolution. In CVPR.Google ScholarCross Ref
- [188] . 2009. Mean squared error: Love it or leave it? A new look at signal fidelity measures. IEEE Signal Processing Magazine 26, 1 (2009), 98–117.Google ScholarCross Ref
- [189] . 2004. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing 13, 4 (2004), 600–612.Google ScholarDigital Library
- [190] . 2020. Deep learning for image super-resolution: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 10 (2020), 3365–3387.Google ScholarCross Ref
- [191] . 2022. Uformer: A general u-shaped transformer for image restoration. In CVPR.Google ScholarCross Ref
- [192] . 2021. Lightweight image super-resolution with multi-scale feature interaction network. In ICME.Google ScholarCross Ref
- [193] . 2023. DR2: Diffusion-based robust degradation remover for blind face restoration. In CVPR.Google ScholarCross Ref
- [194] . 2020. Component divide-and-conquer for real-world image super-resolution. In ECCV.Google ScholarDigital Library
- [195] . 2021. Unsupervised real-world image super resolution via domain-distance aware training. In CVPR.Google ScholarCross Ref
- [196] . 2021. Deflow: Learning complex image degradations from unpaired data with conditional flows. In CVPR.Google ScholarCross Ref
- [197] . 2022. Efficient non-local contrastive attention for image super-resolution. In AAAI.Google ScholarCross Ref
- [198] . 2023. DiffIR: Efficient diffusion model for image restoration. In ICCV.Google Scholar
- [199] . 2021. Boosting high-level vision with joint compression artifacts reduction and super-resolution. In ICPR.Google ScholarCross Ref
- [200] . 2020. Unified dynamic convolutional network for super-resolution with variational degradations. In CVPR.Google ScholarCross Ref
- [201] . 2020. Learning texture transformer network for image super-resolution. In CVPR.Google ScholarCross Ref
- [202] . 2010. Image super-resolution via sparse representation. IEEE Transactions on Image Processing 19, 11 (2010), 2861–2873.Google ScholarDigital Library
- [203] . 2017. Deep edge guided recurrent residual learning for image super-resolution. IEEE Transactions on Image Processing 26, 12 (2017), 5895–5907.Google ScholarDigital Library
- [204] . 2023. Hardware-friendly scalable image super resolution with progressive structured sparsity. In ACMMM.Google ScholarDigital Library
- [205] . 2020. A stereo attention module for stereo image super-resolution. IEEE Signal Processing Letters 27 (2020), 496–500. https://ieeexplore.ieee.org/abstract/document/8998204Google ScholarCross Ref
- [206] . 2017. Light-field image super-resolution using convolutional neural network. IEEE Signal Processing Letters 24, 6 (2017), 848–852.Google ScholarCross Ref
- [207] . 2015. Learning a deep convolutional network for light-field image super-resolution. In ICCVW.Google ScholarDigital Library
- [208] . 2021. Vector-quantized image modeling with improved VQGAN. arXiv:2110.04627. Retrieved from https://arxiv.org/abs/2110.04627Google Scholar
- [209] . 2017. Hallucinating very low-resolution unaligned and noisy face images by transformative discriminative autoencoders. In CVPR.Google ScholarCross Ref
- [210] . 2018. Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In CVPRW.Google ScholarCross Ref
- [211] . 2013. Landmark image super-resolution by retrieving web images. IEEE Transactions on Image Processing 22, 12 (2013), 4865–4878.Google ScholarDigital Library
- [212] . 2022. Restormer: Efficient transformer for high-resolution image restoration. In CVPR.Google ScholarCross Ref
- [213] . 2020. Low resolution face recognition using a two-branch deep convolutional neural network architecture. Expert Systems with Applications 139 (2020), 112854. https://www.sciencedirect.com/science/article/pii/S0957417419305561Google ScholarDigital Library
- [214] . 2010. On single image scale-up using sparse-representations. In ICCS.Google Scholar
- [215] . 2020. Remote sensing image super-resolution via mixed high-order attention network. IEEE Transactions on Geoscience and Remote Sensing 59, 6 (2020), 5183–5196.Google ScholarCross Ref
- [216] . 2018. Super-identity convolutional neural network for face hallucination. In ECCV.Google ScholarDigital Library
- [217] . 2018. Learning a single convolutional super-resolution network for multiple degradations. In CVPR.Google ScholarCross Ref
- [218] Leheng Zhang, Yawei Li, Xingyu Zhou, Xiaorui Zhao, and Shuhang Gu. 2024. Transcending the limit of local window: Advanced super-resolution transformer with adaptive token dictionary. arXiv:2401.08209. Retrieved from https://arxiv.org/abs/2401.08209Google Scholar
- [219] . 2023. ESSAformer: Efficient transformer for hyperspectral image super-resolution. In CVPR.Google ScholarCross Ref
- [220] . 2018. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR.Google ScholarCross Ref
- [221] . 2019. RankSRGAN: Generative adversarial networks with ranker for image super-resolution. In ICCV.Google ScholarCross Ref
- [222] . 2022. Efficient long-range attention network for image super-resolution. In ECCV.Google ScholarDigital Library
- [223] . 2021. Edge-oriented convolution block for real-time super resolution on mobile devices. In ACMMM.Google ScholarDigital Library
- [224] . 2021. Data-free knowledge distillation for image super-resolution. In CVPR.Google ScholarCross Ref
- [225] . 2018. Image super-resolution using very deep residual channel attention networks. In ECCV.Google ScholarDigital Library
- [226] . 2018. Image super-resolution using very deep residual channel attention networks. In ECCV.Google ScholarDigital Library
- [227] Yulun Zhang, Kunpeng Li, Kai Li, Bineng Zhong, and Yun Fu. 2019. Residual non-local attention networks for image restoration. In ICLR.Google Scholar
- [228] . 2018. Residual dense network for image super-resolution. In CVPR.Google ScholarCross Ref
- [229] . 2021. Context reasoning attention network for image super-resolution. In ICCV.Google ScholarCross Ref
- [230] . 2019. Image super-resolution by neural texture transfer. In CVPR.Google ScholarCross Ref
- [231] . 2019. Channel splitting network for single MR image super-resolution. IEEE Transactions on Image Processing 28, 11 (2019), 5649–5662.Google ScholarDigital Library
- [232] . 2018. CrossNet: An end-to-end reference-based super resolution network using cross-scale warping. In ECCV.Google ScholarDigital Library
- [233] . 2015. Learning face hallucination in the wild. In AAAI.Google ScholarCross Ref
- [234] . 2022. Efficient image super-resolution using vast-receptive-field attention. In ECCV.Google Scholar
- [235] . 2022. Towards robust blind face restoration with codebook lookup transformer. In NeurIPS.Google Scholar
- [236] . 2023. SRFormer: Permuted self-attention for single image super-resolution. In ICCV.Google ScholarCross Ref
- [237] . 2022. Blind face restoration via integrating face shape and generative priors. In CVPR.Google ScholarCross Ref
- [238] . 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV.Google ScholarCross Ref
- [239] . 2023. Attention retractable frequency fusion transformer for image super resolution. In CVPR.Google ScholarCross Ref
- [240] . 2016. Deep cascaded bi-network for face hallucination. In ECCV.Google ScholarCross Ref
- [241] . 2011. Internal statistics of a single natural image. In CVPR.Google ScholarDigital Library
Index Terms
- A Systematic Survey of Deep Learning-Based Single-Image Super-Resolution
Recommendations
Single image super-resolution via self-similarity and low-rank matrix recovery
We propose a novel single-image super resolution (SISR) approach using self-similarity of image and the low-rank matrix recovery (LRMR). The method performs multiple upsampling steps with relatively small magnification factors to recover a desired high ...
Texture enhancement for improving single-image super-resolution performance
Although various single-image super-resolution algorithms have been developed to increase image resolution, they still do not provide adequate performance in the texture region due to the lack of fine textures in the processed image. In this paper, we ...
Fast Learning-Based Single Image Super-Resolution
We present a learning-based single image super-resolution (SISR) method to obtain a high resolution (HR) image from a single given low resolution (LR) image. Our method gives more accurate results while also testing (runs) and training faster with a ...
Comments