Abstract
In recent years, image super-resolution (SR) based on deep learning technology has made significant progress. However, most methods are difficult to apply in real life because of their large parameters and heavy computation. Recently, residual learning has been widely applied to the problem of super-resolution. It can make the shallow features extracted from the input image act on each middle layer through long and short connection. Therefore, residual learning can be focused on processing high-frequency feature information, which significantly improves the SR performance of the network. However, with the improvement of network depth, the features that can be effectively utilized are still the shallow ones extracted from the input image. In this paper, we propose the feature separation and fusion network(FSFN). We further enrich the high-frequency feature information by separating and fusing the extracted and unextracted features in the internal shallow layer of each feature separation and fusion module. As the depth of the network increases, the shallow features extracted from the input image can be updated in a direction closer to those extracted from the real high-resolution image. A large number of experimental results show that this method has a strong performance compared with the existing SR algorithm with similar parameters and computation.
Similar content being viewed by others
References
Agustsson E, Timofte R (2017) NTIRE 2017 challenge on single image super-resolution: Dataset and study. In: CVPR, pp 1122–1131
Ahn N, Kang B, Sohn K (2018) Fast, accurate, and lightweight super-resolution with cascading residual network. In: ECCV, pp 256–272
Allebach JP, Wong PW (1996) Edge-directed interpolation. In: Proceedings 1996 International conference on image processing, Lausanne, Switzerland, September 16-19, 1996, pp 707–710
Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel M (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: British machine vision conference, BMVC 2012, Surrey, UK, September 3-7, 2012, pp 1–10
Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. In: CVPR, pp 275–282
Chu X, Zhang B, Ma H, Xu R, Li J, Li Q (2019) Fast, accurate and lightweight super-resolution with neural architecture search. arXiv:1901.07261
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38 (2):295–307
Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. In: ECCV, pp 391–407
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778
Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, pp 2261–2269
Huang J, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: CVPR, pp 5197–5206
Hui Z, Gao X, Yang Y, Wang X (2019) Lightweight image super-resolution with information multi-distillation network. In: Proceedings of the 27th ACM International conference on multimedia, MM 2019, Nice, France, October 21-25, 2019, pp 2024–2032
Irani M, Peleg S (1991) Improving resolution by image registration. CVGIP Graph Model. Image Process. 53(3):231–239
Jin X, Xiong Q, Xiong C, Li Z, Gao Z (2019) Single image super-resolution with multi-level feature fusion recursive network. Neurocomputing 370:166–173
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: CVPR, pp 1646–1654
Kim J, Lee JK, Lee KM (2016) Deeply-recursive convolutional network for image super-resolution. In: CVPR, pp 1637–1645
Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: 3rd International conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings
Lai W, Huang J, Ahuja N, Yang M (2019) Fast and accurate image super-resolution with deep laplacian pyramid networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(11):2599–2613
Li X, Orchard MT (2000) New edge directed interpolation. In: Proceedings of the 2000 international conference on image processing, ICIP 2000, Vancouver, BC, Canada, September 10-13, 2000, pp 311–314
Lim B, Son S, Kim H, Nah S, M Lee K (2017) Enhanced deep residual networks for single image super-resolution. In: CVPR, pp 1132–1140
Liu B, Ait-Boudaoud D (2020) Effective image super resolution via hierarchical convolutional neural network. Neurocomputing 374:109–116
Liu J, Zhang W, Tang Y, Tang J, Wu G (2020) Residual feature aggregation network for image super-resolution. In: CVPR, pp 2356–2365
Martin DR, Fowlkes CC, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, pp 416–425
Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, Aizawa K (2017) Sketch-based manga retrieval using manga109 dataset. Multim. Tools Appl. 76(20):21811–21838
Qiu Y, Wang R, Tao D, Cheng J (2019) Embedded block residual network: A recursive restoration model for single-image super-resolution. In: ICCV, pp 4179–4188
Ren C, He X, Pu Y, Nguyen TQ (2019) Enhanced non-local total variation model and multi-directional feature prediction prior for single image super resolution. IEEE Trans. Image Process. 28(8):3778–3793
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: CVPR, pp 1874–1883
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. In: CVPR, pp 2790–2798
Tai Y, Yang J, Liu X, Xu C (2017) Memnet: A persistent memory network for image restoration. In: ICCV, pp 4549–4557
Tai Y, Yang J, Liu X, Xu C (2017) Memnet: A persistent memory network for image restoration. In: ICCV, pp 4549–4557
Tong T, Li G, Liu X, Gao Q (2017) Image super-resolution using dense skip connections. In: ICCV, pp 4809–4817
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 X, Gu Y, Gao X, Hui Z (2019) Dual residual attention module network for single image super resolution. Neurocomputing 364:269–279
Yang X, Mei H, Zhang J, Xu K, Yin B, Zhang Q, Wei X (2019) DRFN: deep recurrent fusion network for single-image super-resolution with large factors. IEEE Trans. Multimed 21(2):328–337
Yang W, Wang W, Zhang X, Sun S, Liao Q (2019) Lightweight feature fusion network for single image super-resolution. IEEE Signal Process. Lett. 26 (4):538–542
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: Curves and surfaces - 7th international conference, Avignon, France, June 24-30, 2010, Revised Selected Papers, pp 711–730
Zhang K, Gool LV, Timofte R (2020) Deep unfolding network for image super-resolution. In: CVPR, pp 3214–3223
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep residual channel attention networks. In: ECCV, pp 294–310
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep residual channel attention networks. In: ECCV, pp 294–310
Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. In: CVPR, pp 2472–2481
Zhang Z, Wang X, Jung C (2019) DCSR: dilated convolutions for single image super-resolution. IEEE Trans. Image Process. 28(4):1625–1635
Zhang L, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans. Image Process. 15 (8):2226–2238
Acknowledgment
This work was supported in part by the National Natural Science Foundation of China (61876099), in part by the National Key R&D Program of China (2019YFB1311001), in part by the National Natural Science Foundation of China (U1806202), in part by the National Natural Science Foundation of China (61533011), in part by the Scientific and Technological Development Project of Shandong Province (2019GSF111002), in part by the Shenzhen Science and Technology Research and Development Funds (JCYJ20180305164401921), in part by the Foundation of Ministry of Education Key Laboratory of System Control and Information Processing (Scip201801), and in part by the Foundation of State Key Laboratory of Integrated Services Networks (ISN20-06). Kai Zhu and Zhenxue Chen contributed equally to this work and should be considered as the co-first authors.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Kai Zhu and Zhenxue Chen have contributed equally.
Rights and permissions
About this article
Cite this article
Zhu, K., Chen, Z., Wu, Q.M.J. et al. FSFN: feature separation and fusion network for single image super-resolution. Multimed Tools Appl 80, 31599–31618 (2021). https://doi.org/10.1007/s11042-021-11121-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11121-6