Page 327 - 《软件学报》2021年第12期

江泽涛 等:一种基于 MDARNet 的低照度图像增强方法 3991

[21] Wang F, David MJT. Survey on the Attention based RNN model and its applications in computer vision. arXiv preprint arXiv:1601.
06823, 2016.
[22] Ashish V, Noam S, Niki P, et al. Attention is All You Need. NIPS 2017: In: Proc. of the 31st Int’l Conf. on Neural Information
Processing Systems, 2017. 6000−6010.
[23] Zhang H, Goodfellow I, Metaxas D, et al. Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318, 2018.
[24] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition
(CVPR). 2018. 7132−7141.
[25] Chen D, He ZW, Cao YP, et al. Deep neural network for fast and accurate single image super-resolution via channel-
attention-based fusion of orientation-aware features. arXiv preprint arXiv: 1912.04016, 2019.
[26] Wang Y, Cao Y, Zha ZJ, et al. Progressive Retinex: Mutually reinforced illumination-noise perception network for low light image
enhancement. In: Proc. of the 27th ACM Int’l Conf. on Multimedia (MM 2019). 2019. 1−9. [doi: 10.1145/3343031.3350983]
[27] Lv FF, Lu F. Attention-guided low-light image enhancement. arXiv preprint arXiv: 1908.00682, 2019. 1−12.
[28] Qin LL. Research on low-light image enhancement based on generative adversarial networks [MS. Thesis]. Guilin: Guilin
University of Electronic Technology, 2020 (in Chinese with English abstact).
[29] Gao H, Zhuang L, Laurens VDM, et al. Densely connected convolutional networks. In: Proc. of the IEEE Conf. on Computer
Vision and Pattern Recognition (CVPR). 2017. 4700−4708. [doi: 10.1109/CVPR.2017.243]
[30] Ding XH, Guo YC, Ding GG, et al. ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution
blocks. arXiv preprint arXiv: 1908.03930, 2019.
[31] Lee C, Lee C, Kim CS. Contrast enhancement based on layered difference representation. In: Proc. of the 19th IEEE Int’l Conf. on
Image Processing (ICIP). Orlando, 2013. 965−968. [doi: 10.1109/ICIP.2012.6467022]
[32] Chen ZY, Jiang TT, Tian YH. Quality assessment for comparing image enhancement algorithms. In: Proc. of the IEEE Conf. on
Computer Vision and Pattern Recognition (CVPR). Ohio, 2014. 3003−3010. [doi: 10.1109/CVPR.2014.384]
[33] Vonikakis V, Kouskouridas R, Gasteratos A. On the evaluation of illumination compensation algorithms. Multimedia Tools &
Applications, 2018,77:9211−9231.
[34] Brown M, Susstrunk S. Multi-spectral SIFT for scene category recognition. In: Proc. of the IEEE Conf. on Computer Vision and
Pattern Recognition (CVPR). 2011. 177−184. [doi: 10.1109/CVPR.2011.5995637]
[35] Loh YP, Chan CS. Getting to know low-light images with the exclusively dark dataset. Computer Vision and Image Understanding,
2019,178:30−42. [doi: 10.1016/j.cviu.2018.10.010]

附中文参考文献:
[18] 江泽涛,覃露露.一种基于 U-Net 生成对抗网络的低照度图像增强方法.电子学报,2020,48(2):258−264.
[19] 江泽涛,伍旭,张少钦.一种基于 MR-VAE 的低照度图像增强方法.计算机学报,2019,12:1−13. http://kns.cnki.net/kcms/detail/11.
1826.TP.20191202.1403.002.html
[28] 覃露露.基于生成对抗网络的低照度图像增强方法研究[硕士学位论文].桂林:桂林电子科技大学,2020

江泽涛(1961－),男,博士,教授,博士生导 秦嘉奇(1993－),男,硕士,主要研究领域为
师 , 主要 研究 领域 为 深 度 学 习 , 计算 机 计算机视觉.
视觉.

覃露露(1993－),女,硕士,主要研究领域为 张少钦(1962－),女,教授,主要研究领域为
深度学习,计算机视觉. 图像处理,力学行为关系.