Abstract
Image super-resolution reconstruction is a research hotspot in the field of computer vision. Traditional image super-resolution reconstruction methods based on deep learning mostly up-sample low-resolution images ignoring categories and instances, which will cause some problems such as unrealistic texture in the reconstructed images or sawtooth phenomenon on the edge of instance. In this manuscript, we propose an image super-resolution reconstruction method based on instance spatial feature modulation and feedback mechanism. First, the prior knowledge of instance spatial features is introduced in the reconstruction process. Instance spatial features of low-resolution images are extracted to modulate super-resolution reconstruction features. Then, based on the feedback mechanism, the modulated low-resolution image features are iteratively optimized for the reconstruction results, so that the model can finally learn instance-level reconstruction ability. Experiments on COCO-2017 show that, compared with traditional deep learning-based image super-resolution reconstruction methods, the proposed method can obtain better image reconstruction results, and the reconstructed images have more realistic instance textures.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available on request from the corresponding author Hanxu Jiang.
References
Tong T, Li G, Liu X et al (2017) Image super-resolution using dense skip connections[C]// 2017 IEEE international conference on computer vision (ICCV), Venice, pp. 4799-4807
Lim B, Son S, Kim H et al (2017) Enhanced deep residual networks for single image super-resolution[C]// 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), Honolulu, pp. 1132-1140
Haris M, Shakhnarovich G, Ukita N (2018) Deep back-projection networks for super-resolution[C]// 2018 IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, pp. 3606–3616
Wang X, Yu K, Dong C et al (2018) Recovering realistic texture in image super-resolution by deep spatial feature transform[C]// 2018 IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, pp. 606–615
Zhen L, Jing L Y, Zheng L et al (2019) Feedback network for image super-resolution[C]// 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Long Beach, pp 3867–3876
Tai Y W, Liu S, Brown M S et al (2010) Super-resolution using edge prior and single image detail synthesis[C]// IEEE conference on computer vision and pattern recognition(CVPR), San Francisco, pp. 2400-2407
Timofte R, De S V, Van G L. (2013) Anchored neighborhood regression for fast example-based super-resolution[C]// IEEE international conference on computer vision (ICCV), Sydney, pp. 1920-1927
Timofte R, De SV, Van GL (2014) A+: adjusted anchored neighborhood regression for fast super-resolution[C]// Asian conference on computer vision(ACCV), Singapore, pp. 111-126
Huang JB, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars[C]// IEEE conference on computer vision and pattern recognition (CVPR), Boston, pp. 5197-5206
Peleg T, Elad M (2014) A statistical prediction model based on sparse representations for single image super-resolution[J]. IEEE Trans Image Process 23(6):2569–2582
Schulter S, Leistner C, Bischof H. (2015) Fast and accurate image upscaling with super-resolution forests[C]// IEEE conference on computer vision and pattern recognition (CVPR), Boston, pp 3791–3799
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks[J]. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
Dong C, Loy C C, He K et al (2014) Learning a deep convolutional network for image super-resolution [C]// European conference on computer vision (ECCV), Zurich, pp 184–199
Dong C, Loy C C, Tang X (2016) Accelerating the super-resolution convolutional neural network[C]// European conference on computer vision (ECCV), Amsterdam, pp 391–407
Shi W, Caballero J, Huszár F et al (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]// IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 1874–1883
Ledig C, Theis L, Huszar F et al (2017) Photo-realistic single image super-resolution using a generative adversarial network[C]// IEEE conference on computer vision and pattern recognition(CVPR), Honolulu, pp 105–114
Yu J, Fan Y, Yang J et al (2018) Wide activation for efficient and accurate image super-resolution[C]// IEEE conference on computer vision and pattern recognition(CVPR), Salt Lake City, pp 2621–2624
Hui Z, Li J, Gao X et al (2021) Progressive perception-oriented network for single image super-resolution[J]. Inf Sci 546:769–786
Du X (2022) Single image super-resolution using global enhanced upscale network[J]. Appl Intell 52:2813–2819
Wang Z, Lu Y, Li W et al (2021) Single image super-resolution with attention-based densely connected module[J]. Neurocomputing 453:876–884
Zhang Y, Tian Y, Kong Y et al (2018) Residual dense network for image super-resolution[C]// IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, pp. 2472–2481
Kim J, Lee J K, Lee K M (2016) Deeply-recursive convolutional network for image super-resolution[C]// IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp. 1637–1645
Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network[C]// IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, pp. 3147–3155
Zhang Y, Li K, Li K et al (2018) Image super-resolution using very deep residual channel attention networks[C]// European conference on computer vision (ECCV), Munich, pp. 286–301
Wang X, Yu K, Wu S et al (2018) ESRGAN: enhanced super-resolution generative adversarial networks[C]// European conference on computer vision (ECCV), Munich, pp. 63-79
Lin TY, Maire M, Belongie S et al (2014) Microsoft COCO: common objects in context[C]// European conference on computer vision (ECCV), Zurich, pp. 740–755
Tai Y, Yang J, Liu X et al (2017) MemNet: a persistent memory network for image restoration[C]// IEEE international conference on computer vision (ICCV), Venice, pp. 4539-4547
Niu B, Wen W, Ren W et al (2020) Single image super-resolution via a holistic attention network[C]// European conference on computer vision(ECCV), Cham, pp 191–207
Ying T, Jian Y, Liu X (2017) Image super-resolution via deep recursive residual network[C]// IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, pp. 3147–3155
Woo S, Park J, Lee JY et al (2018) CBAM: convolutional block attention module[C]// European conference on computer vision (ECCV), Munich, pp 3–19
Wang L, Wang Y, Lin Z et al (2021) Learning a single network for scale-arbitrary super-resolution[C]// Proceedings of the IEEE/CVF international conference on computer vision (ICCV), Montreal, pp. 4801-4810
Kong X, Zhao H, Qiao Y et al (2021) ClassSR: a general framework to accelerate super-resolution networks by data characteristic[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 12016-12025
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
Fu, L., Jiang, H., Wu, H. et al. Image super-resolution reconstruction based on instance spatial feature modulation and feedback mechanism. Appl Intell 53, 601–615 (2023). https://doi.org/10.1007/s10489-022-03625-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03625-x