Single image super-resolution: a comprehensive review and recent insight

doi:10.1007/s11704-023-2588-9

Front. Comput. Sci.

2024, Vol. 18

Issue (1) : 181702 https://doi.org/10.1007/s11704-023-2588-9

Image and Graphics

Single image super-resolution: a comprehensive review and recent insight

Hanadi AL-MEKHLAFI, Shiguang LIU(

)

College of Intelligence and Computing, Tianjin University, Tianjin 300350, China

Download: PDF(9593 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Super-resolution (SR) is a long-standing problem in image processing and computer vision and has attracted great attention from researchers over the decades. The main concept of SR is to reconstruct images from low-resolution (LR) to high-resolution (HR).It is an ongoing process in image technology, through up-sampling, de-blurring, and de-noising. Convolution neural network (CNN) has been widely used to enhance the resolution of images in recent years. Several alternative methods use deep learning to improve the progress of image super-resolution based on CNN. Here, we review the recent findings of single image super-resolution using deep learning with an emphasis on distillation knowledge used to enhance image super-resolution., it is also to highlight the potential applications of image super-resolution in security monitoring, medical diagnosis, microscopy image processing, satellite remote sensing, communication transmission, the digital multimedia industry and video enhancement. Finally, we present the challenges and assess future trends in super-resolution based on deep learning.

Keywords super-resolution deep learning single-image interpolation-based learning-based reconstruction-based

Corresponding Author(s): Shiguang LIU

Just Accepted Date: 02 February 2023 Issue Date: 23 April 2023

Cite this article:

Hanadi AL-MEKHLAFI,Shiguang LIU. Single image super-resolution: a comprehensive review and recent insight[J]. Front. Comput. Sci., 2024, 18(1): 181702.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-023-2588-9
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I1/181702

Fig.1 The taxonomy for single image super-resolution

Fig.2 Illustration of image super-resolution. (a) Degradation model; (b) low and high super-resolution

Interpolation	Description
Nearest neighbor	It computes the new value pixel to be interpolated through is the closest neighbor pixel.
Bilinear	It computes the new value pixel to be interpolated is the value of its surrounding pixels bilinearly.
Bicubic	It computes $4 × 4$ pixels around the unknown pixel to do cubic interpolation.

Tab.1 Comparison between several interpolation methods

Method	Concept	Details	Dataset(scale): PSNR/SSIM	Time
ANR	Anchored Neighborhood Regression	Sparse dictionary and regressor anchored	Set14( $× 3$ ): 28.65/0.8093	0.69
A+	Adjusted Anchored Neighborhood Regression	Decision tree and extreme learning machine	Set14( $× 3$ ): 29.13/0.8188	0.69

Tab.2 Example for traditional methods

Method	Concept	Keywords	Parameters	Mult-Adds	Dataset(scale):PSNR/SSIM
SRCNN	Super-Resolution Convolutional Neural Network	Deep convolutional neural network	57K	52.7G	Set14( $× 4$ ): 27.50/0.7513
VDSR	Very Deep Super-Resolution	Residual learning	665K	612.6G	Set14( $× 4$ ): 28.01/0.7674
DRRN	Deep Recursive Residual Network	Recursive and residual connections	297K	6,796.9G	Set14( $× 4$ ): 28.21/0.7720
DRCN	Deeply-Recursive Convolutional Network	Recursive-supervision and skip-connections	1,774K	17,974.3G	Set14( $× 4$ ): 28.02/0.7670
FSRCNN	Fast Super-Resolution Convolutional Neural Network	Re-design the SRCNN, deconvolution layer	12K	4.6G	Set14( $× 4$ ): 27.61/0.7550
IMDN	Information Multi-Distillation Network	Channel attention	715K	58.53G	Set14( $× 4$ ): 28.58/0.7811
RFDN	Residual Feature Distillation Network	Feature distillation connection	550K	33.13G	Set14( $× 4$ ): 27.50/0.7513
CARN	Cascading mechanism on A Residual Network	Cascading mechanism	1,592K	90.9G	Set14( $× 4$ ): 28.60/0.7806
CBPN	Compact Back-Projection Network	Cascading up- and down-sampling layers	1,197K	97.9G	Set14( $× 4$ ): 28.63/0.7813
MSRN	Multi-Scale residual Network for image Super-Resolution	Multi-hierarchical Feature fusion	4219K	349.9G	Set14( $× 4$ ): 28.60/0.7751
MCSN	Multi-Scale Channel attention Network	Multi-scale feature fusion, channel shuffle attention mechanism and global feature fusion connection	1581K	728.4G	Set14( $× 4$ ): 28.73/0.7847

Tab.3 Different lightweight methods

Method	Concept	Keywords	Parameters	Mult-Adds	Dataset(scale): PSNR/SSIM
RCAN	Residual channel attention network	Channel-attention-based convolution neural network	16M	?	Set14( $× 4$ ): 28.87/0.7889
SENet	Squeeze-and-Excitation Network	Stacking a collection of Squeeze-and-Excitation blocks	28.1M	3.87G	ImageNet:?/?
SESR	Squeeze and Excitation Super-Resolution	Recursive squeeze and excitation networks	624K	?	Set14( $× 4$ ): 28.32/0.784
ScSE	Spatial and channel Squeeze and Excitation	Concurrent spatial and channel SE blocks	$3.3 × 104$	?	?
SAN	Second-order Attention Neural network	Second-order channel attention, non-locally enhanced residual group	15.7M	?	Set14( $× 4$ ): 28.92/0.7888
SelNet	Deep Network with Selection units	selection unit(SU)	1,417K	83.1G	Set14( $× 4$ ): 28.49/0.7783
DRLN	Densely Residual Laplacian Network	Laplacian pyramid attention	$3.4 × 104$	?	Set14( $× 4$ ): 28.94/0.7900
RNAN	Residual Non-Local Attention Networks	Non local attention	7.5M	?	Set14( $× 4$ ): 28.83/0.7878
CSFM	Channel-wise and Spatial Feature Modulation	Spatial and channel attention mechanisms	(12-13)M	?	Set14( $× 4$ ): 28.87/0.7886
RAM	Residual Attention Module	Residual spatial and channel attention	1389K	?	Set14( $× 4$ ): 33.57/?
RFANet	Residual Feature Aggregation Network	Feature aggregation	11M	?	Set14( $× 4$ ): 28.88/0.7894
UAN	Upsampling attention network	Non-local and local skip connection in residual attention groups (RAGs)	15.7M	?	Set14( $× 4$ ): 28.92/0.7789

Tab.4 Different attention methods

Fig.3 Residual and dense learning methods. (a) EDSR, (b) D-DBPN, (c) SRDenseNet, (d) RDN, (e) SRMD, and (f) KARN

Method	Concept	Details	Parameters	Mult-Adds	Dataset(scale):PSNR/SSIM
EDSR/ MDSR	Enhanced Deep Super-Resolution / Multi-scale Deep Super-Resolution	Removing unnecessary modules in conventional residual networks/ Using different upscaling factors	EDSR: 43M / MDSR: 8M	EDSR: 2890.0G/ MDSR: 407.5G	Set14( $× 4$ ): 28.80/0.7876
SRMDNF	Super-Resolution Multiple Degradation Noise-Free	Multiple degradation, convolutional neural network	1555K	89.3G	Set14( $× 4$ ): 28.35/0.7787
RDN	Residual Dense Network	Residual dense block	23M	–	Set14( $× 4$ ): 28.81/.7871
SR-DenseNet	Super-Resolution Dense Network	Dense skip connections	–	–	Set14( $× 4$ ): 28.50/0.7782
MixNet	Mixed Link Network	Residual network, dense network and Dual Path Network	48.5M	–	CIFAR-10: 4.19
ESPCNN	Efficient Sub-Pixel Convolutional Neural Network	Sub-pixel convolution	58K	–	Set14( $× 4$ ): 27.73/?
KARN	Kernel-Attended Residual Network	Multi-channel fusion, kernel-attended and space-feature re-calibration	15M	–	Set14( $× 4$ ): 28.73/0.785
D-DBPN	Dense-Deep Back-Projection Networks	Dense connections with back-projection units	10M	5715.4G	Set14( $× 4$ ): 28.82/0.786

Tab.5 Different residual and dense learning methods

Fig.4 Generative adversarial networks (GANs). (a) SRGAN [74], (b) ZSSR [75], (c) ESRGAN [76], and (d) RankSRGAN [79]

Tab.6 Different GAN methods

Method	Concept	Keywords	Details	Parameters	Dataset(scale): PSNR/SSIM
KernelGAN	Kernel generative adversarial network	Internal-GAN	● It estimated kernel based on the image patch recurrence property.● GAN used to generate images.● From the generator is derived the blur kernel.● A generator is used to re-downscale the LR image, and a discriminator is used to ensure cross-scale patch similarity.	151K	KernelGAN+USRNet for DIV2K( $× 4$ ): 23.69/0.6539
FKP	Flow-based kernel prior	Kernel prior	● It improved KernelGAN [81] and Double-DIP [84,89].● it used USRNet [88] to generate the output of SR based on the kernel estimation.	143K	KernelGAN-FKP + USRNet for DIV2K( $× 4$ ): 25.46/0.7229
SRSVD	Blind Image Super-Resolution with Spatially Variant Degradations	Kernel discriminator	● Degradation-aware generator network used to generate HR image.● A kernel discriminator used to identify the errors.● kernel parameters reconstructed using a kernel discriminator to analyze artifacts that built by a Degradation-aware generator network.	< 2M	BSD100 : 29.92/0.846
IKC	Iterative Kernel Correction	Blur kernel estimation	● It is based on the predict-and-correct principle.● It used spatial feature transform layers for multiple blur kernels.	?	Set14( $× 4$ ): 28.26/0.7688

Tab.7 Different Blind super resolution methods

Fig.5 Example for Blind super resolution method: IKC (Gu et al. [82])

Fig.6 Overview of distillation knowledge SR structure

Fig.7 Knowledge distillation methods. (a) TNSR/SNSR [93], (b) FAKD [94], (c) PISR [95], (d) IDN [97], and (e) DFKD [98]

Method	Concept	Details	Parameters	Mult-Adds	Dataset(scale): PSNR/SSIM
TNSR/ SNSR	Teacher Network for SR / Student Network for SR	● To propagate knowledge, the features are extracted from the networks as Satistical maps.	TNSR=805.83K and SNSR=81.67K	TNSR=2.593G and SNSR=0.271G	TNSR-Set14( $× 4$ ): 28.43/- and SNSR-Set14( $× 4$ ): 27.43
FAKD	Feature Affinity-based Knowledge Distillation	● It used feature map correlation.● It introduced distilling the feature-affinity matrix of the strategy of teacher-student network.● It improved the performance of RCAN [54] and SAN [58] using the teacher network (TN) and student network (SN).	Tn-RCAN=15.59M and SN-RCAN= 5.17M	Tn-RCAN=36.80G and SN-RCAN= 12.93G	TN-RCAN-Set14( $× 4$ ): 28.851/0.7885 and SN-RCAN-Set14( $× 4$ ): 28.750/ 0.7859
PISR	Privileged Information for SR	● Ground-truth high-resolution (HR) images as privileged information.● It improved the performance of FSRCNN.	13K	4.6G	Set14( $× 4$ ): 27.77/0.7615
AIL	Adaptive importance learning	● Learnable pixel-wise importance map.● It improved the performance of VDSR [18].	(VDSR-f32+AIL)= 166K	(VDSR-f32+AIL)= 642M	(VDSR-f32+AIL)-Set14( $× 4$ ): 0.14/0.0041
IDN	Information Distillation Network	● Stacked information distillation.● The key of IDN is the information distillation block.● The local long and short path characteristics were extracted by combining the enhancement and compression units.	553K	89.0G	Set14( $× 4$ ): 28.25/0.7730
DDRN	Deep distillation recursive network	● Multi-scale purification unit, ultra-dense residual blocks	297K	6,796.9G	Set14( $× 4$ ): 28.21/0.7720
DFKD	Data-free knowledge distillation	● Iterative and progressive training strategy.● It developed EDSR [66] and VDSR [18] models.	–	–	EDSR-Set14( $× 4$ ): 28.33/0.7758 and VDSR-Set14( $× 4$ ): 27.73/0.7617

Tab.8 Different knowledge distillation methods

1	G, Freedman R Fattal . Image and video upscaling from local self-examples. ACM Transactions on Graphics, 2011, 30( 2): 12
2	D, Glasner S, Bagon M Irani . Super-resolution from a single image. In: Proceedings of the 12th IEEE International Conference on Computer Vision. 2009, 349−356
3	J, Yang Z, Lin S Cohen . Fast image super-resolution based on in-place example regression. In: Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2013, 1059−1066
4	M, Bevilacqua A, Roumy C, Guillemot M L A Morel . Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of British Machine Vision Conference (BMVC). 2012, 135.1−135.10
5	H, Chang D-Y, Yeung Y Xiong . Super-resolution through neighbor embedding. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.; vol. 1. 2004, I–I
6	W T, Freeman E C, Pasztor O T Carmichael . Learning low-level vision. International Journal of Computer Vision, 2000, 40( 1): 25–47
7	K, Jia X, Wang X Tang . Image transformation based on learning dictionaries across image spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35( 2): 367–380
8	R, Timofte Smet V, De Gool L Van . Anchored neighborhood regression for fast example-based super-resolution. In: Proceedings of 2013 IEEE International Conference on Computer Vision. 2013, 1920−1927
9	J, Yang Z, Wang Z, Lin S, Cohen T Huang . Coupled dictionary training for image super-resolution. IEEE Transactions on Image Processing, 2012, 21( 8): 3467–3478
10	J, Yang J, Wright T, Huang Y Ma . Image super-resolution as sparse representation of raw image patches. In: Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. 2008, 1−8
11	J, Yang J, Wright T S, Huang Y Ma . Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 2010, 19( 11): 2861–2873
12	Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. In: Proceedings of the 7th International Conference on Curves and Surfaces. 2010, 711−730
13	W, Yang X, Zhang Y, Tian W, Wang J H, Xue Q Liao . Deep learning for single image super-resolution: a brief review. IEEE Transactions on Multimedia, 2019, 21( 12): 3106–3121
14	Zhou L, Feng S. A review of deep learning for single image super-resolution. In: Proceedings of International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS). 2019, 139–142
15	Ha V K, Ren J, Xu X, Zhao S, Xie G, Vargas V M. Deep learning based single image super-resolution: A survey. In: Proceedings of the 9th International Conference on Brain Inspired Cognitive Systems. 2018, 106−119
16	H, Zhang P, Wang C, Zhang Z Jiang . A comparable study of CNN-based single image super-resolution for space-based imaging sensors. Sensors, 2019, 19( 14): 3234
17	C, Dong C C, Loy K, He X Tang . Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38( 2): 295–307
18	J, Kim J K, Lee K M Lee . Accurate image super-resolution using very deep convolutional networks. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1646−1654
19	Dong C, Loy C C, Tang X. Accelerating the super-resolution convolutional neural network. In: Proceedings of the 14th European Conference on Computer Vision. 2016, 391–407
20	J, Kim J K, Lee K M Lee . Deeply-recursive convolutional network for image super-resolution. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1637−1645
21	X, Li Y, Wu W, Zhang R, Wang F Hou . Deep learning methods in real-time image super-resolution: a survey. Journal of Real-Time Image Processing, 2020, 17( 6): 1885–1909
22	Z, Wang J, Chen S C H Hoi . Deep learning for image super-resolution: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43( 10): 3365–3387
23	S M A, Bashir Y, Wang M, Khan Y Niu . A comprehensive review of deep learning-based single image super-resolution. PeerJ Computer Science, 2021, 7: e621
24	A, Liu Y, Liu J, Gu Y, Qiao C Dong . Blind image super-resolution: A survey and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 1–9
25	H, Zhu C, Xie Y, Fei H Tao . Attention mechanisms in CNN-based single image super-resolution: a brief review and a new perspective. Electronics, 2021, 10( 10): 1187
26	J, Tian K K Ma . A survey on super-resolution imaging. Signal, Image and Video Processing, 2011, 5( 3): 329–342
27	Shah A J, Gupta S B. Image super resolution-a survey. In: Proceedings of the 1st International Conference on Emerging Technology Trends in Electronics, Communication & Networking. 2012, 1−6
28	Ghesu F C, Köhler T, Haase S, Hornegger J. Guided image super-resolution: a new technique for photogeometric super-resolution in hybrid 3-D range imaging. In: Jiang X, Hornegger J, Koch R, eds. Pattern Recognition. Cham: Springer, 2014, 227−238
29	S Moitra . Single-image super-resolution techniques: a review. International Journal for Science and Advance Research in Technology, 2017, 3( 4): 271–283
30	D, Huang H Liu . A short survey of image super resolution algorithms. Journal of Computer Science Technology Updates, 2015, 2( 2): 19–29
31	R R, Schultz R L Stevenson . A Bayesian approach to image expansion for improved definition. IEEE Transactions on Image Processing, 1994, 3( 3): 233–242
32	Y, Wang W, Wan R, Wang X Zhou . An improved interpolation algorithm using nearest neighbor from VTK. In: Proceedings of 2010 International Conference on Audio, Language and Image Processing. 2010, 1062−1065
33	J, Titus S Geroge . A comparison study on different interpolation methods based on satellite images. International Journal of Engineering Research & Technology, 2013, 2( 6): 82–85
34	P, Parsania D Virparia . A review: Image interpolation techniques for image scaling. International Journal of Innovative Research in Computer and Communication Engineering, 2014, 2( 12): 7409–7414
35	X, Li M T Orchard . New edge-directed interpolation. IEEE Transactions on Image Processing, 2001, 10( 10): 1521–1527
36	A B, Gavade P Sane . Super resolution image reconstruction by using bicubic interpolation. In: Proceedings of National Conference on Advanced Technologies in Electrical and Electronic Systems. 2014, 1
37	M, Irani S Peleg . Improving resolution by image registration. CVGIP: Graphical Models and Image Processing, 1991, 53( 3): 231–239
38	R, Nayak D Patra . Enhanced iterative back-projection based super-resolution reconstruction of digital images. Arabian Journal for Science and Engineering, 2018, 43( 12): 7521–7547
39	H, Stark P Oskoui . High-resolution image recovery from image-plane arrays, using convex projections. Journal of the Optical Society of America A, 1989, 6( 11): 1715–1726
40	C, Fan C, Wu G, Li J Ma . Projections onto convex sets super-resolution reconstruction based on point spread function estimation of low-resolution remote sensing images. Sensors, 2017, 17( 2): 362
41	R R, Schultz R L Stevenson . Improved definition video frame enhancement. In: Proceedings of 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 1995, 2169−2172
42	R R, Schultz R L Stevenson . Extraction of high-resolution frames from video sequences. IEEE Transactions on Image Processing, 1996, 5( 6): 996–1011
43	J Besag . On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society: Series B: (Methodological), 1986, 48( 3): 259–279
44	Homem M R P, Martins A L D, Mascarenhas N D A. Super-resolution image reconstruction using the discontinuity adaptive ICM. 1994. Poster, https://www.dca.fee.unicamp.br/~ting/misc/anais-poster-2007/posters/33629.pdf
45	Timofte R, De Smet V, Van Gool L. A+: Adjusted anchored neighborhood regression for fast super-resolution. In: Proceedings of the 12th Asian Conference on Computer Vision. 2014, 111−126
46	Y, Wen B, Sheng P, Li W, Lin D D Feng . Deep color guided coarse-to-fine convolutional network cascade for depth image super-resolution. IEEE Transactions on Image Processing, 2019, 28( 2): 994–1006
47	Y, Tai J, Yang X Liu . Image super-resolution via deep recursive residual network. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017, 2790−2798
48	Z, Hui X, Gao Y, Yang X Wang . Lightweight image super-resolution with information multi-distillation network. In: Proceedings of the 27th ACM International Conference on Multimedia. 2019, 2024−2032
49	Ahn N, Kang B, Sohn K A. Fast, accurate, and lightweight super-resolution with cascading residual network. In: Proceedings of the 15th European Conference on Computer Vision. 2018, 256−272
50	Zhu F, Zhao Q. Efficient single image super-resolution via hybrid residual feature learning with compact back-projection network. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision Workshop. 2019, 2453−2460
51	J, Li F, Fang K, Mei G Zhang . Multi-scale residual network for image super-resolution. In: Proceedings of the 15th European Conference on Computer Vision (ECCV). 2018, 517−532
52	J, Liu J, Tang G Wu . Residual feature distillation network for lightweight image super-resolution. In: Proceedings of European Conference on Computer Vision. 2020, 41−55
53	W, Li J, Li J, Li Z, Huang D Zhou . A lightweight multi-scale channel attention network for image super-resolution. Neurocomputing, 2021, 456: 327–337
54	Y, Zhang K, Li K, Li L, Wang B, Zhong Y Fu . Image super-resolution using very deep residual channel attention networks. In: Proceedings of 15th European Conference on Computer Vision (ECCV). 2018, 294−310
55	J, Hu L, Shen G Sun . Squeeze-and-excitation networks. In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 7132−7141
56	Cheng X, Li X, Yang J, Tai Y. SESR: Single image super resolution with recursive squeeze and excitation networks. In: Proceedings of the 24th International Conference on Pattern Recognition (ICPR). 2018, 147−152
57	A G, Roy N, Navab C Wachinger . Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks. In: Proceedings of 21st International Conference on Medical Image Computing and Computer-Assisted Intervention. 2018, 421−429
58	T, Dai J, Cai Y, Zhang S T, Xia L Zhang . Second-order attention network for single image super-resolution. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019, 11057−11066
59	J S, Choi M Kim . A deep convolutional neural network with selection units for super-resolution. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2017, 1150−1156
60	S, Anwar N Barnes . Densely residual Laplacian super-resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44( 3): 1192–1204
61	Y, Zhang K, Li K, Li B, Zhong Y Fu . Residual non-local attention networks for image restoration. 2019, arXiv preprint arXiv: 1903.10082
62	Y, Hu J, Li Y, Huang X Gao . Channel-wise and spatial feature modulation network for single image super-resolution. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30( 11): 3911–3927
63	J H, Kim J H, Choi M, Cheon J S Lee . Ram: Residual attention module for single image super-resolution. 2018, arXiv preprint arXiv: 1811.12043v1
64	J, Liu W, Zhang Y, Tang J, Tang G Wu . Residual feature aggregation network for image super-resolution. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020, 2356−2365
65	Z, Zheng Y, Jiao G Fang . Upsampling attention network for single image super-resolution. In: Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. 2021, 399−406
66	B, Lim S, Son H, Kim S, Nah K M Lee . Enhanced deep residual networks for single image super-resolution. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2017, 1132−1140
67	K, Zhang W, Zuo L Zhang . Learning a single convolutional super-resolution network for multiple degradations. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 3262−3271
68	Y, Zhang Y, Tian Y, Kong B, Zhong Y Fu . Residual dense network for image super-resolution. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 2472−2481
69	T, Tong G, Li X, Liu Q Gao . Image super-resolution using dense skip connections. In: Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). 2017, 4809–4817
70	Wang W, Li X, Yang J, Lu T. Mixed link networks. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence. 2018, 2819−2825
71	W, Shi J, Caballero F, Huszár J, Totz A P, Aitken R, Bishop D, Rueckert Z Wang . Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 1874−1883
72	M, Haris G, Shakhnarovich N Ukita . Deep back-projection networks for super-resolution. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 1664−1673
73	Y, Dun Z, Da S, Yang Y, Xue X Qian . Kernel-attended residual network for single image super-resolution. Knowledge-Based Systems, 2021, 213: 106663
74	C, Ledig L, Theis F, Huszár J, Caballero A, Cunningham A, Acosta A, Aitken A, Tejani J, Totz Z, Wang W Shi . Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017, 105−114
75	A, Shocher N, Cohen M Irani . Zero-shot super-resolution using deep internal learning. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2018, 3118−3126
76	X, Wang K, Yu S, Wu J, Gu Y, Liu C, Dong Y, Qiao CC Loy . ESRGAN: Enhanced super-resolution generative adversarial networks. In: Proceedings of European Conference on Computer Vision. 2018, 63−79
77	Jolicoeur-Martineau A. The relativistic discriminator: a key element missing from standard GAN. In: Proceedings of the 7th International Conference on Learning Representations. 2019
78	Szegedy C, Ioffe S, Vanhoucke V, Alemi A A. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017, 4278−4284
79	W, Zhang Y, Liu C, Dong Y Qiao . RankSRGAN: Generative adversarial networks with ranker for image super-resolution. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. 2019, 3096−3105
80	S Maeda . Unpaired image super-resolution using pseudo-supervision. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020, 288−297
81	S, Bell-Kligler A, Shocher M Irani . Blind super-resolution kernel estimation using an internal-GAN. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 26
82	J, Gu H, Lu W, Zuo C Dong . Blind super-resolution with iterative kernel correction. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019, 1604−1613
83	T, Michaeli M Irani . Nonparametric blind super-resolution. In: Proceedings of IEEE International Conference on Computer Vision. 2013, 945−952
84	D, Ren K, Zhang Q, Wang Q, Hu W Zuo . Neural blind deconvolution using deep priors. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020, 3338−3347
85	K, Zhang L V, Gool R Timofte . Deep unfolding network for image super-resolution. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020, 3214−3223
86	J, Liang K, Zhang S, Gu L V, Gool R Timofte . Flow-based kernel prior with application to blind super-resolution. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021, 10596−10605
87	Z, Luo Y, Huang S, Li L, Wang T Tan . Unfolding the alternating optimization for blind super resolution. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020
88	L, Wang Y, Wang X, Dong Q, Xu J, Yang W, An Y Guo . Unsupervised degradation representation learning for blind super-resolution. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021, 10576−10585
89	Gandelsman Y, Shocher A, Irani M. “Double-DIP”: Unsupervised image decomposition via coupled deep-image-Priors. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 11018−11027
90	V, Cornillère A, Djelouah Y Wang . Sorkine-Hornung O, Schroers C. Blind image super-resolution with spatially variant degradations. ACM Transactions on Graphics, 2019, 38( 6): 166
91	He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, 770–778
92	J, Gou B, Yu S J, Maybank D Tao . Knowledge distillation: a survey. International Journal of Computer Vision, 2021, 129( 6): 1789–1819
93	Gao Q, Zhao Y, Li G, Tong T. Image super-resolution using knowledge distillation. In: Proceedings of the 14th Asian Conference on Computer Vision (ACCV). 2018, 527−541
94	He Z, Dai T, Lu J, Jiang Y, Xia S T. Fakd: feature-affinity based knowledge distillation for efficient image super-resolution. In: Proceedings of 2020 IEEE International Conference on Image Processing (ICIP). 2020, 518−522
95	Lee W, Lee J, Kim D, Ham B. Learning with privileged information for efficient image super-resolution. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 465−482
96	L, Zhang P, Wang C, Shen L, Liu W, Wei Y, Zhang Den Hengel A Van . Adaptive importance learning for improving lightweight image super-resolution network. International Journal of Computer Vision, 2020, 128( 2): 479–499
97	Z, Hui X, Wang X Gao . Fast and accurate single image super-resolution via information distillation network. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 723−731
98	Zhang Y, Chen H, Chen X, Deng Y, Xu C, Wang Y. Data-free knowledge distillation for image super-resolution. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021, 7848–7857
99	K, Jiang Z, Wang P, Yi J, Jiang J, Xiao Y Yao . Deep distillation recursive network for remote sensing imagery super-resolution. Remote Sensing, 2018, 10( 11): 1700
100	Lu T, Yang W, Wan Y. Super-resolution for surveillance video via adaptive block-matching registration. In: Proceedings of 2015 International Conference on Artificial Intelligence and Industrial Engineering. 2015, 1−3
101	J, Shao F, Chao M, Luo J Lin . A super-resolution reconstruction algorithm for surveillance video. Journal of Forensic Science and Medicine, 2017, 3( 1): 26
102	Ghazali N N A N, Zamani N A, Abdullah S N H S, Jameson J. Super resolution combination methods for CCTV forensic interpretation. In: Proceedings of the 12th International Conference on Intelligent Systems Design and Applications (ISDA). 2012, 853−858
103	H, Yu D, Liu H, Shi H, Yu Z, Wang X, Wang B, Cross M, Bramler T S Huang . Computed tomography super-resolution using convolutional neural networks. In: Proceedings of 2017 IEEE International Conference on Image Processing (ICIP). 2017, 3944−3948
104	H, Greenspan G, Oz N, Kiryati S Peled . MRI inter-slice reconstruction using super-resolution. Magnetic Resonance Imaging, 2002, 20( 5): 437–446
105	J, Yu L, Lavery K Kim . Super-resolution ultrasound imaging method for microvasculature in vivo with a high temporal accuracy. Scientific Reports, 2018, 8( 1): 13918
106	J S, Isaac R Kulkarni . Super resolution techniques for medical image processing. In: Proceedings of 2015 International Conference on Technologies for Sustainable Development (ICTSD). 2015, 1−6
107	S C, Park M K, Park M G Kang . Super-resolution image reconstruction: a technical overview. IEEE Signal Processing Magazine, 2003, 20( 3): 21–36
108	D, Kouame M Ploquin . Super-resolution in medical imaging: An illustrative approach through ultrasound. In: Proceedings of 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. 2009, 249−252
109	S, He Y, Tian S, Feng Y, Wu X, Shen K, Chen Y, He Q, Sun X, Li J, Xu Z L, Wen J Y Qu . In vivo single-cell lineage tracing in zebrafish using high-resolution infrared laser-mediated gene induction microscopy. eLife, 2020, 9: e52024
110	M G, Jones A, Khodaverdian J J, Quinn M M, Chan J A, Hussmann R, Wang C, Xu J S, Weissman N Yosef . Inference of single-cell phylogenies from lineage tracing data using Cassiopeia. Genome Biology, 2020, 21: 92
111	V, Andresen K, Pollok J L, Rinnenthal L, Oehme R, Günther H, Spiecker H, Radbruch J, Gerhard A, Sporbert Z, Cseresnyes A E, Hauser R Niesner . High-resolution intravital microscopy. PLoS One, 2012, 7( 12): e50915
112	A, Small S Stahlheber . Fluorophore localization algorithms for super-resolution microscopy. Nature Methods, 2014, 11( 3): 267–279
113	M Orrit . Celebrating optical nanoscopy. Nature Photonics, 2014, 8( 12): 887
114	A, Singh J S Sidhu . Super resolution applications in modern digital image processing. International Journal of Computer Applications, 2016, 150( 2): 6–8
115	UI Hoque M R, Burks R, Kwan C, Li J. Deep learning for remote sensing image super-resolution. In: Proceedings of the 10th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON). 2019, 286–292
116	H, Zhu X, Tang J, Xie W, Song F, Mo X Gao . Spatio-temporal super-resolution reconstruction of remote-sensing images based on adaptive multi-scale detail enhancement. Sensors, 2018, 18( 2): 498
117	J, Guo X, Gong W, Wang X, Que J Liu . SASRT: semantic-aware super-resolution transmission for adaptive video streaming over wireless multimedia sensor networks. Sensors, 2019, 19( 14): 3121
118	K, Mithra K S Vishvaksenan . Security and resolution enhanced transmission of medical image through IDMA aided coded STTD system. In: Proceedings of 2017 International Conference on Communication and Signal Processing (ICCSP). 2017, 2061−2065
119	K Hayat . Multimedia super-resolution via deep learning: a survey. Digital Signal Processing, 2018, 81: 198–217
120	Bishop C M, Blake A, Marthi B. Super-resolution enhancement of video. In: Proceedings of the 9th International Workshop on Artificial Intelligence and Statistics. 2003, 25–32
121	Gallego N P, Del J Ilao . Multiple-image super-resolution on mobile devices: an image warping approach. EURASIP Journal on Image and Video Processing, 2017, 2017( 1): 8
122	M, Hassaballah K M Hosny . Recent Advances in Computer Vision: Theories and Applications. Cham: Springer, 2018
123	Liu D, Soran B, Petrie G, Shapiro L. A review of computer vision segmentation algorithms. 2012Lecture notes 53, 2012.
124	F, Liu J, Wang S, Zhu M, Gleicher Y Gong . Visual-quality optimizing super resolution. Computer Graphics Forum, 2009, 28( 1): 127–140
125	Hirst D, Rilliard A, Aubergé V. Comparison of subjective evaluation and an objective evaluation metric for prosody in text-to-speech synthesis. In: Proceedings of the 3rd ESCA/COCOSDA Workshop on Speech Synthesis. 1998, 1−4
126	A. R. Reibman and T. Schaper, “Subjective performance evaluation for super-resolution image enhancement,” in Second Int. Wkshp on Video Proc. and Qual. Metrics (VPQM’06), 2006 https://ece.uwaterloo.ca/~z70wang/publications/ICIP12b.pdf
127	S, Opozda A Sochan . The survey of subjective and objective method for quality assessment of 2D and 3D images. Theoretical and Applied Informatics, 2014, 26(1−2): 39−67
128	Th. Alpert and J.-P. Evain, “Subjective quality evaluation - the SSCQE and DSCQE methodologies,” EBU technical review, Spring, See tech. ebu. ch/docs/techreview/trev_271-evain. pdf website, 1997, 12−20
129	Int. Telecommun. Union, Methodology for the Subjective Assessment of the Quality of Television Pictures ITU-R Recommendation BT.500-9, Tech. Rep., See itu. int/rec/R-REC-BT. 500-11-200206-S/en website, 2002
130	Z, Wang A C, Bovik H R, Sheikh E P Simoncelli . Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 2004, 13( 4): 600–612
131	B, Yan B, Bare C, Ma K, Li W Tan . Deep objective quality assessment driven single image super-resolution. IEEE Transactions on Multimedia, 2019, 21( 11): 2957–2971
132	H R, Sheikh A C, Bovik Veciana G De . An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Transactions on Image Processing, 2005, 14( 12): 2117–2128
133	Sheikh H R, Bovik A C. A visual information fidelity approach to video quality assessment. In: The first international workshop on video processing and quality metrics for consumer electronics; vol. 7. 2005, 2117–2128
134	Yeganeh H, Rostami M, Wang Z. Objective quality assessment for image super-resolution: a natural scene statistics approach. In: Proceedings of the 19th IEEE International Conference on Image Processing. 2012, 1481−1484
135	Wang X, Jiang G, Yu M. Reduced reference image quality assessment based on Contourlet domain and natural image statistics. In: Proceedings of the 5th International Conference on Image and Graphics. 2009, 45−50
136	Al Madeed N, Awan Z, Al Madeed S. Image quality assessment-a survey of recent approaches. In: Proceedings of the 8th International Conference on Computer Science, Engineering and Applications. 2018, 143−156
137	H M, Keshk M M, Abdel-Aziem A S, Ali M A Assal . Performance evaluation of quality measurement for super-resolution satellite images. In: Proceedings of 2014 Science and Information Conference. 2014, 364−371
138	X, Zhu Y, Cheng J, Peng R, Wang M, Le X Liu . Super-resolved image perceptual quality improvement via multifeature discriminators. Journal of Electronic Imaging, 2020, 29( 1): 013017
139	Y, Blau T Michaeli . The perception-distortion tradeoff. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 6228−6237
140	A, Mittal R, Soundararajan A C Bovik . Making a "completely blind" image quality analyzer. IEEE Signal Processing Letters, 2012, 20( 3): 209–212
141	C, Ma C Y, Yang X, Yang M H Yang . Learning a no-reference quality metric for single-image super-resolution. Computer Vision and Image Understanding, 2017, 158: 1–16
142	Y, Blau R, Mechrez R, Timofte T, Michaeli L Zelnik-Manor . The 2018 PIRM challenge on perceptual image super-resolution. In: Proceedings of European Conference on Computer Vision. 2018, 334−355

[1]

FCS-22588-OF-HA_suppl_1

Download

[1]	Jingyu LIU, Shi CHEN, Li SHEN. A comprehensive survey on graph neural network accelerators[J]. Front. Comput. Sci., 2025, 19(2): 192104-.
[2]	Lingling ZHAO, Shitao SONG, Pengyan WANG, Chunyu WANG, Junjie WANG, Maozu GUO. A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries[J]. Front. Comput. Sci., 2024, 18(5): 185329-.
[3]	Enes DEDEOGLU, Himmet Toprak KESGIN, Mehmet Fatih AMASYALI. A robust optimization method for label noisy datasets based on adaptive threshold: Adaptive-k[J]. Front. Comput. Sci., 2024, 18(4): 184315-.
[4]	Hengyu LIU, Tiancheng ZHANG, Fan LI, Minghe YU, Ge YU. A probabilistic generative model for tracking multi-knowledge concept mastery probability[J]. Front. Comput. Sci., 2024, 18(3): 183602-.
[5]	Mingzhi YUAN, Kexue FU, Zhihao LI, Manning WANG. Decoupled deep hough voting for point cloud registration[J]. Front. Comput. Sci., 2024, 18(2): 182703-.
[6]	Mingzhen LI, Changxi LIU, Jianjin LIAO, Xuegui ZHENG, Hailong YANG, Rujun SUN, Jun XU, Lin GAN, Guangwen YANG, Zhongzhi LUAN, Depei QIAN. Towards optimized tensor code generation for deep learning on sunway many-core processor[J]. Front. Comput. Sci., 2024, 18(2): 182101-.
[7]	Yufei ZENG, Zhixin LI, Zhenbin CHEN, Huifang MA. Aspect-level sentiment analysis based on semantic heterogeneous graph convolutional network[J]. Front. Comput. Sci., 2023, 17(6): 176340-.
[8]	Yamin HU, Hao JIANG, Zongyao HU. Measuring code maintainability with deep neural networks[J]. Front. Comput. Sci., 2023, 17(6): 176214-.
[9]	Muazzam MAQSOOD, Sadaf YASMIN, Saira GILLANI, Maryam BUKHARI, Seungmin RHO, Sang-Soo YEO. An efficient deep learning-assisted person re-identification solution for intelligent video surveillance in smart cities[J]. Front. Comput. Sci., 2023, 17(4): 174329-.
[10]	Ke-Jia CHEN, Mingyu WU, Yibo ZHANG, Zhiwei CHEN. SR-AFU: super-resolution network using adaptive frequency component upsampling and multi-resolution features[J]. Front. Comput. Sci., 2023, 17(1): 171307-.
[11]	Tian WANG, Jiakun LI, Huai-Ning WU, Ce LI, Hichem SNOUSSI, Yang WU. ResLNet: deep residual LSTM network with longer input for action recognition[J]. Front. Comput. Sci., 2022, 16(6): 166334-.
[12]	Yi WEI, Mei XUE, Xin LIU, Pengxiang XU. Data fusing and joint training for learning with noisy labels[J]. Front. Comput. Sci., 2022, 16(6): 166338-.
[13]	Donghong HAN, Yanru KONG, Jiayi HAN, Guoren WANG. A survey of music emotion recognition[J]. Front. Comput. Sci., 2022, 16(6): 166335-.
[14]	Pinzhuo TIAN, Yang GAO. Improving meta-learning model via meta-contrastive loss[J]. Front. Comput. Sci., 2022, 16(5): 165331-.
[15]	Tian WANG, Shiye LEI, Youyou JIANG, Choi CHANG, Hichem SNOUSSI, Guangcun SHAN, Yao FU. Accelerating temporal action proposal generation via high performance computing[J]. Front. Comput. Sci., 2022, 16(4): 164317-.

Viewed

Full text

Abstract

Cited

Shared

Discussed