Abstract
Deep learning methods for super-resolution (SR) have been dominating in terms of performance in recent years. Such methods can potentially improve the digital zoom capabilities of most modern mobile phones, but are not directly applicable on device, due to hardware constraints. In this work, we adapt MobileNetV3 blocks, shown to work well for classification, detection and segmentation, to the task of super-resolution. The proposed models with the modified MobileNetV3 block are shown to be efficient enough to run on modern mobile phones with an accuracy approaching that of the much heavier, state-of-the-art (SOTA) super-resolution approaches.
H. Wang, V. Bhaskara, A. Levinshtein—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This is why this task is sometimes called image hallucination.
- 2.
ESRGAN [41] takes 2.69 s on a V100 GPU, and 10.46 GB of memory, to generate a 12MP (\(3000 \times 4000\)) output – a standard photo size for a mobile camera. Obtaining the same output using mobile phone hardware would be prohibitively slow, or impossible, due to limited memory.
References
Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: Dataset and study. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017
Ahn, N., Kang, B., Sohn, K.-A.: Fast, accurate, and lightweight super-resolution with cascading residual network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 256–272. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_16
Baker, S., Kanade, T.: Hallucinating faces. In: Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), pp. 83–88. IEEE (2000)
Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding (2012)
Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., Shelhamer, E.: cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)
Chu, X., Zhang, B., Ma, H., Xu, R., Li, J., Li, Q.: Fast, accurate and lightweight super-resolution with neural architecture search. arXiv preprint arXiv:1901.07261 (2019)
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2015)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_25
Elad, M., Feuer, A.: Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images. IEEE Trans. Image Process. 6(12), 1646–1658 (1997)
Farsiu, S., Elad, M., Milanfar, P.: Multiframe demosaicing and super-resolution of color images. IEEE Trans. Image Process. 15(1), 141–159 (2005)
Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multiframe super resolution. IEEE Trans. Image Process. 13(10), 1327–1344 (2004)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Comput. Graphics Appl. 22(2), 56–65 (2002)
Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning low-level vision. Int. J. Comput. Vision 40(1), 25–47 (2000)
Github: FP32 depthwise convolution is slow in GPU (2020). https://github.com/pytorch/pytorch/issues/18631. Accessed 16 July 2020
Gotoh, T., Okutomi, M.: Direct super-resolution and registration using raw CFA images. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004, vol. 2, p. II. IEEE (2004)
Howard, A., et al.: Searching for mobilenetv3. In: ICCV (2019)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Huang, J.B., Singh, A., Ahuja, N.: Single image super-resolution from transformed self-exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5197–5206 (2015)
Hui, Z., Gao, X., Yang, Y., Wang, X.: Lightweight image super-resolution with information multi-distillation network. In: Proceedings of the 27th ACM International Conference on Multimedia. pp. 2024–2032 (2019)
Irani, M., Peleg, S.: Improving resolution by image registration. CVGIP Graphical Models Image Process. 53(3), 231–239 (1991)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43
Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646–1654 (2016)
Kim, K., Kwon, Y.: Example-based learning for singleimage SR and jpeg artifact removal. MPI-TR, (173) 8 (2008)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: 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 (2017)
Learnml: Speeding up model with fusing batch normalization and convolution (2020). https://learnml.today/speeding-up-model-with-fusing-batch-normalization-and-convolution-3. Accessed 31 July 2020
Ledig, C., et al.: 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 (2017)
Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: CVPRW (2017)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: 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. ICCV 2001, vol. 2, pp. 416–423. IEEE (2001)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Dollár, P.: Designing network design spaces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428–10436 (2020)
Sajjadi, M.S., Scholkopf, B., Hirsch, M.: Enhancenet: single image super-resolution through automated texture synthesis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4491–4500 (2017)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR (2016)
Song, D., Xu, C., Jia, X., Chen, Y., Xu, C., Wang, Y.: Efficient residual dense block search for image super-resolution. In: AAAI, pp. 12007–12014 (2020)
Tai, Y., Yang, J., Liu, X., Xu, C.: MemNet: a persistent memory network for image restoration. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4539–4547 (2017)
Takeda, H., Farsiu, S., Milanfar, P.: Robust kernel regression for restoration and reconstruction of images from sparse noisy data. In: 2006 International Conference on Image Processing, pp. 1257–1260. IEEE (2006)
Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4799–4807 (2017)
Tsai, R.: Multiframe image restoration and registration. Adv. Comput. Vis. Image Process. 1, 317–339 (1984)
Vu, T., Nguyen, C.V., Pham, T.X., Luu, T.M., Yoo, C.D.: Fast and efficient image quality enhancement via desubpixel convolutional neural networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 243–259. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_16
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Yu., Loy, C.C.: ESRGAN: enhanced super-resolution generative adversarial networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11133, pp. 63–79. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11021-5_5
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D., et al. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27413-8_47
Zhang, K., Danelljan, M., Li, Y., Timofte, R., et al.: AIM 2020 challenge on efficient super-resolution: methods and results. In: European Conference on Computer Vision Workshops (2020)
Zhang, K., et al.: Aim 2019 challenge on constrained super-resolution: methods and results. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 3565–3574. IEEE (2019)
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 294–310. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_18
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Bhaskara, V., Levinshtein, A., Tsogkas, S., Jepson, A. (2020). Efficient Super-Resolution Using MobileNetV3. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12537. Springer, Cham. https://doi.org/10.1007/978-3-030-67070-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-67070-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67069-6
Online ISBN: 978-3-030-67070-2
eBook Packages: Computer ScienceComputer Science (R0)