Abstract
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion compensation, which is used to estimate the displacement between successive video frames for temporal alignment. Optical flow, which can supply dense and sub-pixel motion between consecutive frames, is among the most common ways for this task. To obtain a good understanding of the effect that optical flow acts in video super-resolution, in this work, we conduct a comprehensive review on this subject for the first time. This investigation covers the following major topics: the function of super-resolution (i.e., why we require super-resolution); the concept of video super-resolution (i.e., what is video super-resolution); the description of evaluation metrics (i.e., how (video) super-resolution performs); the introduction of optical flow based video super-resolution; the investigation of using optical flow to capture temporal dependency for video super-resolution. Prominently, we give an in-depth study of the deep learning based video super-resolution method, where some representative algorithms are analyzed and compared. Additionally, we highlight some promising research directions and open issues that should be further addressed.
Similar content being viewed by others
References
Anwar S, Khan S, Barnes N (2020) A deep journey into super-resolution: a survey. ACM Comput Surv 53(3):1–34
Babacan SD, Molina R, Katsaggelos AK (2011) Variational Bayesian super resolution. IEEE Trans Image Process 20(4):984–999
Baker S, Kanade T (1999) Super-resolution optical flow. Carnegie Mellon University, Pittsburgh, pp 36–99
Baker S, Schar D, Lewis J, Roth S, Black M, Szeliski R (2011) A database and evaluation methodology for optical flow. Int J Comput Vision 92(1):1–31
Bao W, Lai W, Zhang X, Gao Z, Yang M (2019) MEMC-Net: motion estimation and motion compensation driven neural network for video interpolation and enhancement. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2019.2941941
Bian W, Ding S, Xue Y (2017) Fingerprint image super resolution using sparse representation with ridge pattern prior by classification coupled dictionaries. IET Biometr 6(5):342–350
Blau Y, Mechrez R, Timofte R, Michaeli T, Zelnik-Manor L (2018) The 2018 pirm challenge on perceptual image super-resolution. In: Proceedings ECCVW, pp 334–355
Borsoi RA, Costa GH, Bermudez JCM (2019) A new adaptive video super-resolution algorithm with improved robustness to innovations. IEEE Trans Image Process 28(2):673–686
Caballero J, Ledig C, Aitken A, Acosta A, Totz J, Wang Z, Shi W (2017) Real-time video super-resolution with spatio-temporal networks and motion compensation. In: Proceedings CVPR, pp 78–4787
Cai D, Chen K, Qian Y, Kamarainen J (2019) Convolutional low-resolution fine-grained classification. Pattern Recogn Lett 119:166–171
Chan K, Wang X, Yu K, Dong C, Loy C (2021) BasicVSR: the search for essential components in video super-resolution and beyond. In: Proceedings CVPR, pp 4947–4956
Chen Y, Tai Y, Liu X, Shen C, Yang J (2018) FSRNet: end-to-end learning face super-resolution with facial priors. In: Proceedings CVPR, pp 2492–2501
Choi K, Kim C, Kang M, Ra J (2011) Resolution improvement of infrared images using visible image information. IEEE Trans Image Process 18(10):611–614
Cruz C, Mehta R, Katkovnik V, Egiazarian KO (2018) Single image super-resolution based on Wiener filter in similarity domain. IEEE Trans Image Process 27(3):1376–1389
Dai Q, Yoo S, Kappeler A, Katsaggelos AK (2017) Sparse representation-based multiple frame video super-resolution. IEEE Trans Image Process 26(2):765–781
Daithankar MV, Ruikar SD (2020) Video super resolution: a review. In: Proceedings first international conference on data science, machine learning and applications, vol 601, pp 488–495
Dong C, Chen CL, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: Proceedings ECCV, pp 184–199
Dosovitskiy A, Fischer P, Ilg E, Husser P, Hazirbas C, Golkov V, Smagt P, Cremers D, Brox T (2015) FlowNet: learning optical flow with convolutional networks. In: Proceedings ICCV, pp 2758–2766
Drulea M, Nedevschi S (2011) Total variation regularization of local global optical flow. In: Proceedings ITSC, pp 318–323
Eekeren AWM, Schutte K, Vliet LJ (2010) Multiframe super-resolution reconstruction of small moving objects. IEEE Trans Image Process 19(11):2901–2912
Farsiu S, Robinson MD, Elad M, Milanfar P (2004) Fast and robust multiframe super resolution. IEEE Trans Image Process 13(10):1327–1344
Fookes C, Lin F, Chandran V, Sridharan S (2004) Super-Resolved face images using robust optical flow. In: IEEE workshop on the internet, telecommunications and signal processing, pp 391–396
Girshick R, Donahue J, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell 38(1):142–158
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings international conference on artificial intelligence and statistics, pp 249–256
Han T, Kim D, Lee S, Song B (2018) Resolution improvement of infrared images using visible image information. J Vis Commun Image Represent 51:191–200
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution. In: Proceedings CVPR, pp 1664–1673
Haris M, Shakhnarovich G, Ukita N (2019) Recurrent back-projection network for video super-resolution. In: Proceedings CVPR, pp 3897–3906
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings CVPR, pp 770–778
Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670
Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: Proceedings international conference on pattern recognition, pp 2358-2369
Hou L, Yu C, Samaras D (2016) Squared Earth mover’s distance-based loss for training deep neural networks, pp 1–9. arXiv:1611.05916
Huang J, Ma L, Tan T, Wang Y (2003) Learning based resolution enhancement of iris images. Proc BMVC 1:1–10
Huang Y, Wang W, Wang L (2015) Bidirectional recurrent convolutional networks for multi-frame super-resolution. In: Proceedings NIPS, pp 235–243
Huang Y, Shao L, Frangi A (2017) Simultaneous super-resolution and cross-modality synthesis of 3D medical images using weakly-supervised joint convolutional sparse coding. In: Proceedings CVPR, pp 6070–6079
Huang Y, Wang W, Wang L (2018) Video super-resolution via bidirectional recurrent convolutional networks. IEEE Trans Pattern Anal Mach Intell 40(4):1015–1028
Huang Y, Lu Z, Shao Z, Ran M, Zhou J, Fang L, Zhang Y (2019) Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network. Opt Express 27(9):12289–12307
Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T (2017) Flownet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings CVPR, pp 2462–2470
Isobe T, Li S, Jia X, Yuan S, Slabaugh G, Xu C, Li Y, Wang S, Tian Q (2020) Video super-resolution with temporal group attention. In: Proceedings CVPR, pp 8008–8017
Jing X, Zhu X, Wu F, Hu R, You X, Wang Y, Feng H, Yang J (2017) On Bayesian adaptive video super resolution. IEEE Trans Image Process 26(3):1363–1378
Jo Y, Oh S, Kang J, Kim S (2018) Deep video super-resolution network using dynamic upsampling filters without explicit motion compensation. In: Proceedings CVPR, pp 3224–3232
Kalarot R, Porikli F (2019) MultiBoot VSR: multistage multi-reference bootstrapping for video superresolution. In: Proceedings CVPRW, pp 2060–2069
Kappeler A, Yoo S, Dai Q, Katsaggelos A (2016) Video super-resolution with convolutional neural networks. IEEE Trans Comput Imaging 2(2):109–122
Keller S, Lauze F, Nielsen M (2011) Video super-resolution using simultaneous motion and intensity calculations. IEEE Trans Image Process 20(7):1870–1884
Khrulkov V, Babenko A (2021) Neural side-by-side: predicting human preferences for no-reference super-resolution evaluation. In: Proceedings CVPR, pp 4988–4997
Kim K, Kwon Y (2010) Single-image super-resolution using sparse regression and natural image prior. IEEE Trans Pattern Anal Mach Intell 32(6):1127–1133
Kim J, Lee S (2017) Deep learning of human visual sensitivity in image quality assessment framework. In: Proceedings CVPR, pp 1969–1977
Kim T, Sajjadi M, Hirsch M, Scholkopf B (2018) Spatio-temporal transformer network for video restoration. In: Proceedings ECCV, pp 111–127
Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z, Shi W (2017) Photorealistic single image super-resolution using a generative adversarial network. In: Proceedings CVPR, pp 4681–4690
Lei S, Shi Z, Zou Z (2020) Coupled adversarial training for remote sensing image super-resolution. IEEE Trans Geosci Remote Sens 58(5):3633–3643
Li X, Hu Y, Gao X, Tao D, Ning B (2010) A multi-frame image super-resolution method. Signal Process 90:405–414
Li K, Zhu Y, Yang J, Jiang J (2016) Video super-resolution using an adaptive superpixel-guided auto-regressive model. Pattern Recogn 51:59–71
Li D, Liu Y, Wang Z (2019) Video super-resolution using non-simultaneous fully recurrent convolutional network. IEEE Trans Image Process 28(3):1342–1355
Li F, Bai H, Zhao Y (2020) Learning a deep dual attention network for video super-resolution. IEEE Trans Image Process 29:4474–4488
Liao R, Tao X, Li R, Ma Z, Jia J (2015) Video super-resolution via deep draft-ensemble learning. In: Proceedings ICCV, pp 531–539
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings CVPRW, pp 1132–1140
Lin K, Wang G (2018) Hallucinated-IQA: no-reference image quality assessment via adversarial learning. In: Proceedings CVPR, pp 732–741
Lin F, Fookes C, Chandran V, Sridharan S (2005) Investigation into optical flow super-resolution for surveillance applications. In: Proceedings APRS workshop on digital image computing, pp 73–78
Liu C, Sun D (2014) On Bayesian adaptive video super resolution. IEEE Trans Pattern Anal Mach Intell 36(2):346–360
Liu D, Wang Z, Fan Y, Liu X, Wang Z, Chang S, Huang T (2017) Robust video super-resolution with learned temporal dynamics. In: Proceedings ICCV, pp 2507–2515
Liu D, Wang Z, Fan Y, Liu X, Wang Z, Chang S, Wang X, Huang T (2018) Learning temporal dynamics for video super-resolution: a deep learning approach. IEEE Trans Image Process 27(7):3432–3445
Liu H, Ruan Z, Zhao P, Shang F, Yang L, Liu Y (2020) Video super resolution based on deep learning: a comprehensive survey. arXiv:2007.12928
Lucas A, Lopez-Tapia S, Molina R, Katsaggelos AK (2019) Generative adversarial networks and perceptual losses for video super-resolution. IEEE Trans Image Process 28(7):3312–3327
Ma Z, Liao R, Tao X, Xu L, Jia J, Wu E (2015) Handling motion blur in multi-frame super-resolution. In: Proceedings CVPR, pp 5224–5232
Ma C, Yang C, Yang X, Yang M (2017) Learning a no-reference quality metric for single-image super-resolution. Comput Vis Image Underst 158:1–16
Ma C, Jiang Z, Rao Y, Lu J, Zhou J (2020) Deep face super-resolution with iterative collaboration between attentive recovery and landmark estimation. In: Proceedings CVPR, pp 5569–5578
Meur OL, Ebdelli M, Guillemot C (2013) Hierarchical super-resolution-based inpainting. IEEE Trans Image Process 22(10):3779–3790
Mitzel D, Pock T, Schoenemann T, Cremers D (2009) Video super resolution using duality based TV-L1 optical flow. In: Proceedings DAGM 2009: pattern recognition, pp 432–441
Mudenagudi U, Banerjee S, Kalra PK (2011) Space-time super-resolution using graph-cut optimization. IEEE Trans Pattern Anal Mach Intell 33(5):995–1008
Mudunuri S, Biswas S (2016) Low resolution face recognition across variations in pose and illumination. IEEE Trans Pattern Anal Mach Intell 38(5):1034–1040
Na B, Fox GC (2017) Object detection by a super-resolution method and a convolutional neural networks. In: Proceedings IEEE international conference on big data, pp 2263–2269
Nasrollahi K, Moeslund TB (2014) Super-resolution: a comprehensive survey. Mach Vis Appl 25:1423–1468
Nguyen K, Fookes C, Sridharan S, Tistarelli M, Nixon M (2018) Super-resolution for biometrics: a comprehensive survey. Pattern Recogn 78:23–42
Noor DF, Li Y, Li Z, Bhattacharyya S, York G (2019) Multi-scale gradient image super-resolution for preserving SIFT key points in low-resolution images. Signal Process Image Commun 78:236–245
Pan J, Bai H, Dong J, Zhang J, Tang J (2021) Deep blind video super-resolution. In: Proceedings ICCV, pp 4811–4820
Papenberg N, Bruhn A, Brox T, Didas S, Weickert J (2006) Highly accurate optic flow computation with theoretically justified warping. Int J Comput Vis 67(2):141–158
Park S, Park M, Kang M (2003) Super-resolution image reconstruction: a technical overview. IEEE Signal Process Mag 20(3):21–35
Peleg S, Keren D, Schweitzer L (1987) Improving image resolution using subpixel motion. Pattern Recogn Lett 5(3):223–226
Picku LC (2007) Machine learning in multi-frame image super-resolution. Ph.D thesis, University of Oxford, Britain
Prashnani E, Cai H, Mostofi Y, Sen P (2018) PieAPP: perceptual image-error assessment through pairwise preference. In: Proceedings CVPR, pp 1808–1817
Ranjan A, Black M (2017) Optical flow estimation using a spatial pyramid network. In: Proceedings CVPR, pp 4161–4170
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Proceedings MICCAI, pp 234–241
Ryoo MS, Rothrock B, Fleming C, Yang HJ (2017) Privacy-preserving human activity recognition from extreme low resolution. In: Proceedings AAAI, pp 4255–4262
Sajjadi M, Scholkopf B, Hirsch M (2017) Enhancenet: single image super-resolution through automated texture synthesis. In: Proceedings ICCV, pp 4491–4500
Sajjadi M, Vemulapalli R, Brown M (2018) Frame-recurrent video super-resolution. In: Proceedings CVPR, pp 6626–6634
Schoenemann T, Cremers D (2012) A coding-cost framework for super-resolution motion layer decomposition. IEEE Trans Image Process 21(3):1097–1110
Shen CT, Liu HH, Yang MH, Hung YP, Pei SC (2015) Viewing-distance aware super-resolution for high-definition display. IEEE Trans Image Process 24(1):403–418
Shi W, Caballero J, Huszar F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings CVPR, pp 1874–1883
Singh A, Singh J (2020) Survey on single image based super-resolution-implementation challenges and solutions. Multimed Tools Appl 79(3):1641–1672
Su H, Wu Y, Zhou J (2012) Super-resolution without dense flow. IEEE Trans Image Process 21(4):1782–999
Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: Proceedings CVPR, pp 5693–5703
Sun D, Roth S, Black M (2010) Secrets of optical flow estimation and their principles. In: Proceedings CVPR, pp 2432–2439
Talebi H, Milanfar P (2018) NIMA: neural image assessment. IEEE Trans Image Process 27(8):3998–4011
Tang L, Sun K, Liu L, Wang G, Liu Y (2019) A reduced-reference quality assessment metric for super-resolution reconstructed images with information gain and texture similarity. Signal Process Image Commun 79:32–39
Tan W, Yan B, Bare B (2018) Feature super-resolution: make machine see more clearly. In: Proceedings CVPR, pp 3994–4002
Tao X, Gao H, Liao R, Wang J, Jia J (2017) Detail-revealing deep video super-resolution. In: Proceedings ICCV, pp 4472–4480
Tatem AJ, Lewis HG, Atkinson PM, Nixon MS (2001) Super-resolution target identification from remotely sensed images using a Hopfield neural network. IEEE Trans Geosci Remote Sens 39(4):781–796
Thapa D, Raahemifar K, Bobier W, Lakshminarayanan V (2016) A performance comparison among different super-resolution techniques. Comput Electr Eng 54:313–329
Timofte R, Gu S, Wu J, Van Gool L et al (2018) Ntire 2018 challenge on single image super-resolution: methods and results. In: Proceedings CVPRW, pp 965–976
Tsai R, Huang TS (1984) Multiframe image restoration and registration. In: Advances in computer vision and image processing. pp 317–339
Tu Z, Aa Nico, Gemeren C, Veltkamp R (2014) A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recogn 47(5):1926–1940
Tu Z, Xie W, Zhang D, Poppe R, Veltkamp R, Li B, Yuan J (2019) A survey of variational and CNN-based optical flow techniques. Signal Process Image Commun 72:9–24
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Wang Z, Yi P, Jiang K, Jiang J, Han Z, Lu T, Ma J (2019) Multi-memory convolutional neural network for video super-resolution. IEEE Trans Image Process 28(5):2530–2544
Wang L, Li D, Zhu Y, Tian L, Shan Y (2020a) Dual super-resolution learning for semantic segmentation. In: Proceedings CVPR, pp 3774–3783
Wang L, Guo Y, Liu L, Lin Z, Deng X, An W (2020b) Deep video super-resolution using HR optical flow estimation. IEEE Trans Image Process 29:4323–4336
Wang Z, Chen J, Hoi S (2021a) Deep learning for image super-resolution: a survey. IEEE Trans Pattern Anal Mach Intell 43(10):3365–3387
Wang W, Zhang H, Yuan Z, Wang C (2021b) Unsupervised real-world super-resolution: a domain adaptation perspective. In: Proceedings ICCV, pp 4318–4327
Xiang X, Tian Y, Zhang Y, Fu Y, Allebach J, Xu C (2020) Zooming Slow-Mo: fast and accurate one-stage space-time video super-resolution. In: Proceedings CVPR, pp 3370–3379
Xiong Z, Sun X, Wu F (2010) Robust web image/video super-resolution. IEEE Trans Image Process 19(8):2017–2028
Xue T, Chen B, Wu J, Wei D, Freeman W (2019) Video enhancement with task-oriented flow. Int J Comput Vis 127(8):1106–1125
Xu G, Xu J, Li Z, Wang L, Sun X, Cheng M (2021) Temporal modulation network for controllable space-time video super-resolution. In: Proceedings CVPR, pp 6388–6397
Yang W, Feng J, Xie G, Liu J, Guo Z, Yan S (2018) Video super-resolution based on spatial-temporal recurrent residual networks. Comput Vis Image Underst 168:79–92
Yang W, Zhang X, Tian Y, Wang W, Xue JH, Liao Q (2019) Deep learning for single image superresolution: a brief review. IEEE Trans Multimed 21(12):3106–3121
Yang X, Xiang W, Zeng H, Zhang L (2021) Real-world video super-resolution: a benchmark dataset and a decomposition based learning scheme. In: Proceedings ICCV, pp 4781–4790
Yi P, Wang Z, Jiang K, Jiang J, Lu T, Tian X, Ma J (2021) Omniscient video super-resolution. In: Proceedings ICCV, pp 4429–4438
You C, Li G, Zhang Y, Zhang X, Shan H, Li M, Ju S, Zhao Z, Zhang Z, Cong W, Vannier M, Saha P, Hoffman E, Wang G (2020) CT super-resolution GAN constrained by the identical, residual, and cycle learning ensemble (GAN-CIRCLE). IEEE Trans Med Imaging 39(1):188–203
Yuan Z, Wu J, Kamata S, Ahrary A, Yan P (2009) Fingerprint image enhancement by super resolution with early stopping. Proc ICIS 4:527–531
Yuan Q, Zhang L, Shen H, Li P (2010) Adaptive multiple-frame image super-resolution based on U-curve. IEEE Trans Image Process 19(12):3157–3170
Zhang K, Zuo W, Zhang L (2018a) Learning a single convolutional super-resolution network for multiple degradations. In: Proceedings CVPR, pp 3262–3271
Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018b) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings CVPR, pp 586–595
Zhang H, Liu D, Xiong Z (2019) Two-stream action recognition-oriented video super-resolution. In: Proceedings ICCV, pp 8799–8808
Zhao W, Sawhney H (2002) Is super-resolution with optical flow feasible? In: Proceedings ECCV, pp 599–613
Zhao H, Qi X, Shen X, Shi J, Jia J (2018) ICNet for real-time semantic segmentation on high-resolution images. In: Proceedings ECCV, pp 418–434
Zhu H, Li L, Wu J, Dong W, Shi G (2020) MetaIQA: deep meta-learning for no-reference image quality assessment. In: Proceedings CVPR, pp 14143–14152
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant 62106177. It was also supported by the Central University Basic Research Fund of China (Nos. 2042020KF0016, CCNU20TS028), the Teaching research project of CCNU (202013), and the Wuhan University-Infinova project Nos. 2019010019. The numerical calculation was supported by the supercomputing system in the Super-computing Center of Wuhan University.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tu, Z., Li, H., Xie, W. et al. Optical flow for video super-resolution: a survey. Artif Intell Rev 55, 6505–6546 (2022). https://doi.org/10.1007/s10462-022-10159-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-022-10159-8