Abstract
Recent research on image super-resolution (SR) has greatly progressed with the development of convolutional neural networks (CNNs). However, the fixed geometric structures of standard convolution filters largely limit the learning capacity of CNNs for image SR. To effectively address this problem, we propose a deformable and residual convolutional network (DefRCN) for image SR. Specifically, a deformable residual convolution block (DRCB) is developed to augment spatial sampling locations and enhance the transformation modelling capability of CNNs. In addition, we optimize the residual convolution block to reduce the model redundancy and alleviate the vanishing-gradient in backpropagation. In addition, the proposed upsample block allows the network to directly process low-resolution images, which reduces the computational resource cost. Extensive experiments on benchmark datasets verify that the proposed method achieves a high quantitative and qualitative performance.
Similar content being viewed by others
References
Jia K, Wang X, Tang X (2013) Image transformation based on learning dictionaries across image spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(2):367–380
Yang J, Wright J, Huang TS et al (2010) Image super-resolution via sparse representation. IEEE transactions on image processing 19(11):2861–2873
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: International conference on curves and surfaces. Springer, Berlin, pp 711–730
Timofte R, De Smet V, Van Gool L (2014) A+: adjusted anchored neighborhood regression for fast super-resolution. In: Asian conference on computer vision. Springer, Cham, pp 111–126
Yang CY, Yang MH (2013) Fast direct super-resolution by simple functions. In: Proceedings of the IEEE international conference on computer vision, pp 561–568
Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3791–3799
Dong C, Loy CC, He K et al (2016) Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 38(2):295–307
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1646–1654
Kim J, Lee JK, Lee KM (2016) Deeply recursive convolutional network for image super-resolution. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 1637–1645
Lai WS, Huang JB, Ahuja N et al (2017) Deep laplacian pyramid networks for fast and accurate super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 624–632
Tai Y, Yang J, Liu X et al (2017) Memnet: a persistent memory network for image restoration. In: Proceedings of the IEEE international conference on computer vision, pp 4539–4547
Zhang Y, Tian Y, Kong Y et al (2018) Residual dense network for image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2472–2481
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1664–1673
Zhang Y, Li K, Li K et al (2018) Image super-resolution using very deep residual channel attention networks. In: Proceedings of the European conference on computer vision (ECCV), pp 286–301
Gu J, Lu H, Zuo W et al (2019) Blind super-resolution with iterative kernel correction. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1604–1613
Soh JW, Park GY, Jo J et al (2019) Natural and realistic single image super-resolution with explicit natural manifold discrimination. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8122–8131
Lim B, Son S, Kim H et al (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136–144
Liu H, Cao F, Wen C et al (2020) Lightweight multi-scale residual networks with attention for image super-resolution. Knowledge-Based Systems 203:106103
Liu H, Cao F (2020) Improved dual-scale residual network for image super-resolution. Neural Netw 132:84–95
Cao F, Yao K, Liang J (2020) Deconvolutional neural network for image super-resolution. Neural Netw 132:394–404
Cao F, Liu H (2019) Single image super-resolution via multi-scale residual channel attention network. Neurocomputing 358:424–436
Cao F, Chen B (2019) New architecture of deep recursive convolution networks for superresolution. Knowledge-Based Systems 178:98–110
Ledig C, Theis L, Huszr F et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681–4690
Wang X, Yu K, Wu S et al (2018) Esrgan: enhanced super-resolution generative adversarial networks. In: Proceedings of the European conference on computer vision (ECCV), pp 63–79
Shocher A, Cohen N, Irani M (2018) Zero-shot super-resolution using deep internal learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3118–3126
Bulat A, Yang J, Tzimiropoulos G (2018) To learn image super-resolution, use a gan to learn how to do image degradation first. In: Proceedings of the European conference on computer vision (ECCV), pp 185–200
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3147–3155
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Tong T, Li G, Liu X et al (2017) Image super-resolution using dense skip connections. In: Proceedings of the IEEE international conference on computer vision, pp 4799–4807
Jaderberg M, Simonyan K, Zisserman A (2015) Spatial transformer networks. In: Advances in neural information processing systems, pp 2017–2025
Jeon Y, Kim J (2017) Active convolution: learning the shape of convolution for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 4201–4209
Dai J, Qi H, Xiong Y et al (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 764–773
Xu Z, Xu X, Wang L, et al. (2017) Deformable convnet with aspect ratio constrained nms for object detection in remote sensing imagery. Remote Sensing 9(12):1312
Ren Y, Zhu C, Xiao S (2018) Deformable faster r-cnn with aggregating multi-layer features for partially occluded object detection in optical remote sensing images. Remote Sens 10(9):1470
Ouyang W, Wang X, Zeng X et al (2015) Deepid-net: deformable deep convolutional neural networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2403–2412
Zhang M, Li X, Xu M et al (2018) RBC semantic segmentation for sickle cell disease based on deformable U-Net. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 695–702
Sun M, Zhang G, Dang H et al (2019) Accurate gastric cancer segmentation in digital pathology images using deformable convolution and multi-scale embedding networks. IEEE Access 7:75530–75541
Jin Q, Meng Z, Pham TD et al (2019) DUNet: a deformable network for retinal vessel segmentation. Knowledge-Based Systems 178:149–162
Zhu J, Fang L, Ghamisi P (2018) Deformable convolutional neural networks for hyperspectral image classification. IEEE Geosci Remote Sens Lett 15(8):1254–1258
Timofte R, Agustsson E, Van Gool L et al (2017) Ntire 2017 challenge on single image super-resolution: methods and results. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 114–125
Bevilacqua M, Roumy A, Guillemot C et al (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: BMVC
Martin D, Fowlkes C, Tal D et al (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings eighth IEEE international conference on computer vision, pp 416–423
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5197–5206
Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing 13(4):600–612
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
Paszke A, Gross S, Chintala S et al (2017) Automatic differentiation in pytorch
Acknowledgements
This work was supported by the Scientific Research Project of Tianjin Municipal Education Commission [grant number 2019KJ105].The authors also acknowledge the anonymous reviewers for their helpful comments on the manuscript.
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
Zhang, Y., Sun, Y. & Liu, S. Deformable and residual convolutional network for image super-resolution. Appl Intell 52, 295–304 (2022). https://doi.org/10.1007/s10489-021-02246-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02246-0