Abstract
As a popular research field of computer vision, super-resolution is currently widely studied. In the past, the size of the training set required for super-resolution work was too large. A large training set would cause more resource requirements, and at the same time, the time overheads of data transmission would also increase. Moreover, in super-resolution work, the relationship between the complexity of the image and the model structure is usually not considered, and images are recovered in same depth. This method often cannot meet the SR-reconstruction needs of all images. This paper proposes a new training and reconstruction framework based on multiple models. The framework prunes the training set according to the complexity of the images in the training set, which significantly reduces the size of the training set. At the same time, the framework can select the specific depth according to the image features of the images to recover the images, which helps to improve the SR-reconstruction effect. After testing different models, our framework can reduce the amount of training data by 41.9% and reduce the average training time from 2935 min to 2836 min. At the same time, our framework can improve the average SR-reconstruction effect of 65.7% images, optimize the average perceptual index from 3.1607 to 3.0867, and optimize the average SR-reconstruction time from 101.7 s to 66.7 s.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. CoRR abs/1501.00092 (2015). http://arxiv.org/abs/1501.00092
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. CoRR abs/1608.00367 (2016). http://arxiv.org/abs/1608.00367
Fu, Y., Zhang, T., Zheng, Y., Zhang, D., Huang, H.: Hyperspectral image super-resolution with optimized RGB guidance. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Goodfellow, I.J., et al.: Generative adversarial networks. ArXiv abs/1406.2661 (2014)
Gu, J., Lu, H., Zuo, W., Dong, C.: Blind super-resolution with iterative kernel correction. CoRR abs/1904.03377 (2019). http://arxiv.org/abs/1904.03377
Haris, M., Shakhnarovich, G., Ukita, N.: Recurrent back-projection network for video super-resolution. CoRR abs/1903.10128 (2019). http://arxiv.org/abs/1903.10128
Hu, X., Mu, H., Zhang, X., Wang, Z., Tan, T., Sun, J.: Meta-SR: a magnification-arbitrary network for super-resolution. CoRR abs/1903.00875 (2019). http://arxiv.org/abs/1903.00875
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. CoRR abs/1511.04587 (2015). http://arxiv.org/abs/1511.04587
Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. CoRR abs/1511.04491 (2015). http://arxiv.org/abs/1511.04491
Lai, W., Huang, J., Ahuja, N., Yang, M.: Deep Laplacian pyramid networks for fast and accurate super-resolution. CoRR abs/1704.03915 (2017). http://arxiv.org/abs/1704.03915
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. CoRR abs/1609.04802 (2016). http://arxiv.org/abs/1609.04802
Li, S., He, F., Du, B., Zhang, L., Xu, Y., Tao, D.: Fast spatio-temporal residual network for video super-resolution. CoRR abs/1904.02870 (2019). http://arxiv.org/abs/1904.02870
Li, Z., Yang, J., Liu, Z., Yang, X., Jeon, G., Wu, W.: Feedback network for image super-resolution. CoRR abs/1903.09814 (2019). http://arxiv.org/abs/1903.09814
Ma, C., Yang, C., Yang, X., Yang, M.: Learning a no-reference quality metric for single-image super-resolution. CoRR abs/1612.05890 (2016). http://arxiv.org/abs/1612.05890
Mao, X., Shen, C., Yang, Y.: Image restoration using convolutional auto-encoders with symmetric skip connections. CoRR abs/1606.08921 (2016). http://arxiv.org/abs/1606.08921
Mittal, A., Soundararajan, R., Bovik, A.: Making a “completely blind” image quality analyzer. Signal Processing Letters, 20, 209–212 (2013). https://doi.org/10.1109/LSP.2012.2227726
Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections, pp. 4809–4817 (2017). https://doi.org/10.1109/ICCV.2017.514
Wang, L., et al.: Learning parallax attention for stereo image super-resolution. CoRR abs/1903.05784 (2019). http://arxiv.org/abs/1903.05784
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. CoRR abs/1809.00219 (2018). http://arxiv.org/abs/1809.00219
Wang, X., Yu, K., Dong, C., Loy, C.C.: Recovering realistic texture in image super-resolution by deep spatial feature transform. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Yuan, N., Zhu, Z., Wu, X., Shen, L.: MMSR: a multi-model super resolution framework. In: Tang, X., Chen, Q., Bose, P., Zheng, W., Gaudiot, J.-L. (eds.) NPC 2019. LNCS, vol. 11783, pp. 197–208. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30709-7_16
Zhang, K., Zuo, W., Zhang, L.: Deep plug-and-play super-resolution for arbitrary blur kernels. CoRR abs/1903.12529 (2019). http://arxiv.org/abs/1903.12529
Zhang, S., Lin, Y., Sheng, H.: Residual networks for light field image super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Acknowledgement
This work was supported by the National Science Foundation under Grant No. 61972407 and Guangdong Province Key Laboratory of Popular High Performance Computers 2017B030314073.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 IFIP International Federation for Information Processing
About this paper
Cite this paper
Yuan, N., Zhang, D., Wang, Q., Shen, L. (2021). A Multi-model Super-Resolution Training and Reconstruction Framework. In: He, X., Shao, E., Tan, G. (eds) Network and Parallel Computing. NPC 2020. Lecture Notes in Computer Science(), vol 12639. Springer, Cham. https://doi.org/10.1007/978-3-030-79478-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-79478-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79477-4
Online ISBN: 978-3-030-79478-1
eBook Packages: Computer ScienceComputer Science (R0)
