Abstract
With the development of convolutional neural networks, the effectiveness of low-light image enhancement techniques have been greatly advanced. However, the calculate-intensive and memory-intensive characteristics of convolutional neural networks make them difficult to be implemented in mobile platform with low power and limited bandwidth. This paper proposes a complete solution for low-light image enhancement from CNN model to mobile (M2M) FPGA. The proposed solution utilizes a pseudo-symmetry quantization method to compress the low-light image enhancement model, and an accelerator to permit the processing ability of the system significantly. We implemented the whole system on a customized FPGA SOC platform (a low-cost chip, Xilinx Inc. ZYNQ\(^{TM}\)XC7Z035). Extensive experiments show that our method achieved competitive results with the other three platforms, i.e. achieved better speed compare to ARM and CPU; and achieved better power efficiency compared to ARM, CPU, and GPU.
This work was supported by the Natural Science Foundation of China (U1803262, 61602349, and 61440016).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xu, X., Liu, L., Zhang, X., Guan, W., Hu, R.: Rethinking data collection for person re-identification: active redundancy reduction. Pattern Recogn. 113(4), 107827 (2021)
Xu, X., Wang, S., Wang, Z., Zhang, X., Hu, R.: Exploring image enhancement for salient object detection in low light images. ACM Trans. Multimedia Comput. Commun. Appl. 17(8), 1–19 (2020)
Xie, P., Xu, X., Wang, Z., Yamasaki, T.: Unsupervised video person re-identification via noise and hard frame aware clustering, pp. 1–6 (2021)
Mu, N., Xu, X., Zhang, X., Lin, X.: Discrete stationary wavelet transform based saliency information fusion from frequency and spatial domain in low contrast images. Pattern Recogn. Lett. 115, 84–91 (2018)
Mu, N., Xu, X., Zhang, X.: Salient object detection in low contrast images via global convolution and boundary refinement. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 743–751 (2019)
Hu, J., Zhang, H., Song, L., Han, Z., Poor, H.V.: Reinforcement learning for a cellular internet of UAVs: protocol design, trajectory control, and resource management. IEEE Wirel. Commun. 27(1), 116–123 (2020)
Yu, W., Shaobo, W., Xinting, H.: Cooperative path planning of UAVs & UGVs for a persistent surveillance task in urban environments. IEEE Internet Things J. 8, 4906–4919 (2020)
Wang, Y., Ma, X., Wang, J., Wang, H.: Pseudo-3d vision-inertia based underwater self-localization for AUVs. IEEE Trans. Veh. Technol. 69(7), 7895–7907 (2020)
Guo, C., et al.: Zero-reference deep curve estimation for low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1780–1789 (2020)
Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: BMVC, p. 155 (2018)
Wang, R., Zhang, Q., Fu, C.-W., Shen, X., Zheng, W.-S., Jia, J.: Underexposed photo enhancement using deep illumination estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6849–6857 (2019)
Ren, W., et al.: Low-light image enhancement via a deep hybrid network. IEEE Trans. Image Process. 28(9), 4364–4375 (2019)
Zhang, Y., Zhang, J., Guo, X.: Kindling the darkness: a practical low-light image enhancer. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1632–1640 (2019)
Cai, J., Shuhang, G., Zhang, L.: Learning a deep single image contrast enhancer from multi-exposure images. IEEE Trans. Image Process. 27(4), 2049–2062 (2018)
Zhu, M., Pan, P., Chen, W., Yang, Y.: EEMEFN: low-light image enhancement via edge-enhanced multi-exposure fusion network. Proc. AAAI Conf. Artif. Intell. 34, 13106–13113 (2020)
Yang, K.-F., Zhang, X.-S., Li, Y.-J.: A biological vision inspired framework for image enhancement in poor visibility conditions. IEEE Trans. Image Process. 29, 1493–1506 (2019)
Xu, K., Yang, X., Yin, B., Lau, R.W.H.: Learning to restore low-light images via decomposition-and-enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2281–2290 (2020)
Land, E.H.: The retinex theory of color vision. Sci. Am. 237(6), 108–129 (1977)
Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982–993 (2016)
Li, M., Liu, J., Yang, W., Sun, X., Guo, Z.: Structure-revealing low-light image enhancement via robust retinex model. IEEE Trans. Image Process. 27(6), 2828–2841 (2018)
Kim, G., Kwon, D., Kwon, J.: Low-lightgan: low-light enhancement via advanced generative adversarial network with task-driven training. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 2811–2815. IEEE (2019)
Jiang, Y., et al.: EnlightenGAN: deep light enhancement without paired supervision. IEEE Trans. Image Process. 30, 2340–2349 (2021)
Yang, W., Wang, S., Fang, Y., Wang, Y., Liu, J.: From fidelity to perceptual quality: a semi-supervised approach for low-light image enhancement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3063–3072 (2020)
Canran, X., Peng, Z., Xuanzhen, H., Zhang, W., Chen, L., An, F.: FPGA-based low-visibility enhancement accelerator for video sequence by adaptive histogram equalization with dynamic clip-threshold. IEEE Trans. Circuits Syst. I Regul. Pap. 67(11), 3954–3964 (2020)
Zhu, C., Han, S., Mao, H., Dally, W.J.:L Trained ternary quantization. arXiv preprint arXiv:1612.01064 (2016)
Choi, J., Wang, Z., Venkataramani, S., Chuang, P.I.-J., Srinivasan, V., Gopalakrishnan, K.: PACT: parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018)
Dong, Z., Yao, Z., Arfeen, D., Gholami, A., Mahoney, M.W., Keutzer, K.: HAWQ-V2: Hessian aware trace-weighted quantization of neural networks. In: Advances in Neural Information Processing Systems, pp. 18518–18529 (2020)
Shen, S., et al.: Q-BERT: Hessian based ultra low precision quantization of BERT. Proc. AAAI Conf. Artif. Intell. 34, 8815–8821 (2020)
Hegde, K., Yu, J., Agrawal, R., Yan, M., Pellauer, M., Fletcher, C.: UCNN: exploiting computational reuse in deep neural networks via weight repetition. In: 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 674–687. IEEE (2018)
Albericio, J., et al.: Bit-pragmatic deep neural network computing. In: Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture, pp. 382–394 (2017)
Kwon, H., Samajdar, A., Krishna, T.: MERI: enabling flexible dataflow mapping over DNN accelerators via reconfigurable interconnects. ACM SIGPLAN Not. 53(2), 461–475 (2018)
Lu, H., Wei, X., Lin, N., Yan, G., Li, X.: Tetris: re-architecting convolutional neural network computation for machine learning accelerators. In: 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 1–8. IEEE (2018)
Zhang, J., Chen, X., Song, M., Li, T.: Eager pruning: algorithm and architecture support for fast training of deep neural networks. In: 2019 ACM/IEEE 46th Annual International Symposium on Computer Architecture (ISCA), pp. 292–303. IEEE (2019)
Faraone, J., Fraser, N., Blott, M., Leong, P.H.W.: SYQ: learning symmetric quantization for efficient deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4300–4309 (2018)
Han, S., et al.: EIE: efficient inference engine on compressed deep neural network. ACM SIGARCH Comput. Archit. News 44(3), 243–254 (2016)
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., Cong, J.: Optimizing FGPA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 161–170 (2015)
Chen, Y.-H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circ. 52(1), 127–138 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Y., Wang, W., Hu, W., Xu, X. (2021). M2M: Learning to Enhance Low-Light Image from Model to Mobile FPGA. In: Magnenat-Thalmann, N., et al. Advances in Computer Graphics. CGI 2021. Lecture Notes in Computer Science(), vol 13002. Springer, Cham. https://doi.org/10.1007/978-3-030-89029-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-89029-2_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89028-5
Online ISBN: 978-3-030-89029-2
eBook Packages: Computer ScienceComputer Science (R0)