Abstract
In recent years, various deep neural networks have been proposed to improve the performance in the single image super-resolution (SISR) task. The commonly used per-pixel MSE loss function captures less perceptual difference and tends to make the super-resolved images overly smooth, while the perceptual loss function defined on image features extracted from one or two layers of a pretrained network yields more visually pleasing results. We propose a new perceptual loss function via combining features from multiple levels, which incorporates the discrepancy between the reconstruction and the ground truth in different structures. In addition, some variants of the proposed perceptual loss are explored. Extensive quantitative and qualitative comparisons with the state-of-the-art methods demonstrate that our loss function can drive the same network to produce better results when used alone or combined with other loss functions.
Similar content being viewed by others
References
Agustsson E, Timofte R (2017) Ntire 2017 challenge on single image super-resolution: dataset and study. In: IEEE conference on computer vision and pattern recognition workshops (CVPRW) , pp 126–135
Bevilacqua M, Roumy A, Guillemot C, Morel M-LA (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: British machine vision conference
Blau Y, Mechrez R, Timofte R, Michaeli T, Zelnik-Manor L (2018) The pirm challenge on perceptual super resolution. (https://www.pirm2018.org/PIRM-SR.html)
Blau Y, Michaeli T (2018) The Perception-Distortion tradeoff. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6628–6237
Bosse S, Maniry D, Müller KR, Wiegand T, Samek W (2018) Deep neural networks for no-reference and full-reference image quality assessment. IEEE Trans Image Process 27(1):206–219
Bruna J, Sprechmann P, LeCun Y (2016) Super-resolution with deep convolutional sufficient statistics. In: International conference on learning representations (ICLR)
Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European conference on computer vision (ECCV), pp 184–199
Dong C, Loy CC, Tang X (2016) Accelerating the superresolution convolutional neural network. In: European conference on computer vision (ECCV), pp 391–407
Greenspan H (2009) Super-resolution in medical imaging. The Comput J 52 (1):43–63
Hochstein S, Ahissar M (2002) View from the top Hierarchies and reverse hierarchies in the visual system. Neuron 36(5):791–804
Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision (ECCV), pp 694–711
Kim J, Lee JK, Lee KM (2016) Accurate image superresolution using very deep convolutional networks. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1646–1654
Kim J, Lee JK, Lee KM (2016) Deeply-recursive convolutional network for image super-resolution. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1637–1645
Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations (ICLR)
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems (NIPS), pp 1097–1105
Lai W-S, Huang J-B, Ahuja N, Yang M-H (2017) Deep laplacian pyramid networks for fast and accurate superresolution. In: IEEE conference on computer vision and pattern recognition (CVPR) , pp 624–632
Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z, Shi W (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 4681–4690
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 136–144
Mahendran A, Vedaldi A (2016) Visualizing deep convolutional neural networks using natural pre-images. Int J Comput Vis, pp 1–23
Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: IEEE international conference on computer vision (ICCV), pp 416–423
Park S-J, Son H, Cho S, Hong K-S, Lee S (2018) SRFeat: single image super-resolution with feature discrimination. In: European conference on computer vision (ECCV), pp 439–455
Sajjadi MSM, Scholkopf B, Hirsch M (2017) EnhanceNet: single image super-resolution through automated texture synthesis. In: International conference on computer vision (ICCV), pp 4491–4500
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR)
Tan W, Yan B, Bare B (2018) Feature super-resolution: make machine see more clearly. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3994–4002
Tong T, Li G, Liu X, Gao Q (2017) Image super-resolution using dense skip connections. In: International conference on computer vision (ICCV), pp 4799–4807
Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, Qiao Y, Loy CC (2018) ESRGAN: enhanced super-resolution generative adversarial networks. In: European conference on computer vision workshops (ECCVW), pp 63–79
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
Yang C-Y, Ma C, Yang M-H (2014) Single-image super-resolution: a benchmark. In: European conference on computer vision (ECCV), pp 372–386
Yosinski J, Clune J, Nguyen A, Fuchs T, Lipson H (2015) Understanding neural networks through deep visualization. In: International conference on machine learning - deep learning workshop
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: Curves and surfaces, pp 711–730
Zhang L, Zhang H, Shen H, Li P (2010) A super-resolution reconstruction algorithm for surveillance images. Signal Process 90(3):848–859
Zhang R, Isola1 P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 586–595
Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6848–6856
Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 2472–2481
Zhao H, Gallo O, Frosio I, Kautz J (2017) Loss functions for image restoration with neural networks. In: IEEE transactions on computational imaging, vol 3, pp 47–57
Acknowledgements
Thanks to the National Natural Science Foundation of China (No. NSFC-61471067, 81671651), the National Great Science Specific Project (No. 2015ZX03002008), the Beijing Municipal Natural Science Foundation (No. 1472024), Beijing University of Posts and Telecommunications (No. 2013XD-04, 2015XD-02), the Beijing Key Laboratory of Work Safety and Intelligent Monitoring Foundation.
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.
Rights and permissions
About this article
Cite this article
Wu, Q., Fan, C., Li, Y. et al. A novel perceptual loss function for single image super-resolution. Multimed Tools Appl 79, 21265–21278 (2020). https://doi.org/10.1007/s11042-020-08878-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08878-7