Page 326 - 《软件学报》2021年第12期

3990 Journal of Software 软件学报 Vol.32, No.12, December 2021

用非对称卷积和像素注意力模块对图像进行的多尺度卷积和特征融合得到多维度特征图,随后利用密集卷积
块对特征图进一步提取特征,然后利用注意力机制在通道和空间维度上独立地完善卷积特征,最后根据 Retinex
理论将估计到的环境光照和噪声分量从低照度图像中减去,由此得到增强结果图.实验结果表明:MDARNet 能
够有效地提升低照度图像的亮度、对比度,并得到与真实图像更接近的色彩增强和噪声抑制效果.从视觉主观
效果和多项客观指标的结果可以看出,MDARNet 方法的增强效果优于一些主流经典的低照度图像增强算法.

References:
[1] Cheng HD, Shi XJ. A simple and effective histogram equalization approach to image enhancement. Digital Signal Processing, 2004,
14(2):158−170. [doi: 10.1016/j.dsp.2003.07.002]
[2] Siu FT, Nor AMI. Exposure based multi-histogram equalization contrast enhancement for non-uniform illumination images. IEEE
Access, 2019,7:70842−70861. [doi: 10.1109/ACCESS.2019.2918557]
[3] Land EH, Mccann JJ. Lightness and Retinex theory. Journal of the Optical Society of America, 1971,61(1):1−11. [doi: 10.1364/
JOSA.61.000001]
[4] Jobson DJ, Rahman Z, Woodell GA. A multiscale Retinex for bridging the gap between color images and the human observation of
scenes. IEEE Trans. on Image Processing, 1997,6(7):965−976. [doi: 10.1109/83.597272]
[5] Guo X, Li Y, Ling H. LIME: Low-light image enhancement via illumination map estimation. IEEE Trans. on Image Processing,
2017,26(2):982−993. [doi: 10.1109/TIP.2016.2639450]
[6] Li MD, Li JY, Yang WH, et al. Structure-revealing low-light image enhancement via robust retinex model. IEEE Trans. on Image
Processing, 2018,27(6):2828−2841. [doi: 10.1109/TIP.2018.2810539]
[7] Ren XT, Li MD, Cheng WH, et al. Joint enhancement and denoising method via sequential decomposition. In: Proc. of the 2018
IEEE Int’l Symp. on Circuits and Systems (ISCAS). 2018. 1−5. [doi: 10.1109/ISCAS.2018.8351427]
[8] Dong X, Wang G, Pang Y, et al. Fast efficient algorithm for enhancement of low lighting video. In: Proc. of the IEEE Int’l Conf.
on Multimedia and Expo. Barcelona, 2011. 1−6. [doi: 10.1109/ICME.2011.6012107]
[9] Ying ZQ, Li G, Ren YR, et al. A new image contrast enhancement algorithm using exposure fusion framework. In: Proc. of the
Int’l Conf. on Computer Analysis of Images and Patterns. 2017. 36−46. [doi: 10.1007/978-3-319-64698-5_4]
[10] Ying ZQ, Li G, Ren YR, et al. A new low-light image enhancement algorithm using camera response model. In: Proc. of the Int’l
Conf. on Computer Vision Workshop (ICCVW). 2017. 3015−3022. [doi: 10.1109/ICCVW.2017.356]
[11] Shen L, Yue ZH, Fan F, et al. MSR-net: Low-light image enhancement using deep convolutional network. arXiv preprint arXiv:
1711.02488, 2017.
[12] Lv FF, Lu F, Wu JH, et al. MBLLEN: Low-light image/video enhancement using CNNs. In: Proc. of the British Machine Vision
Conf. (BMVC). 2018. 1−13.
[13] Tao L, Zhu C, Song JW, et al. Low-light image enhancement using CNN and bright channel prior. In: Proc. of the 2017 IEEE Int’l
Conf. on Image Processing. 2017. 3215−3219. [doi: 10.1109/ICIP.2017.8296876]
[14] Tao L, Zhu C, Xiang GQ, et al. LLCNN: A convolutional neural network for low-light image enhancement. In: Proc. of the IEEE
Visual Communications & Image Processing. 2018. 1−4. [doi: 10.1109/VCIP.2017.8305143]
[15] Wei H, Xia YS. Low-light image enhancement based on joint generative adversarial network and image quality assessment. In:
Proc. of the 2018 11th Int’l Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).
Beijing, 2018. 1−6. [doi: 10.1109/CISP-BMEI.2018.8633150]
[16] Wang WJ, Wei C, Yang WH, et al. GLADNet: Low-light enhancement network with global awareness. In: Proc. of the IEEE Int’l
Conf. on Automatic Face & Gesture Recognition. 2018. 1−12. [doi: 10.1109/FG.2018.00118]
[17] Zhang YH, Zhang JW, Guo XJ. Kindling the darkness: A practical low-light image enhancer. arXiv preprint arXiv: 1905.04161,
2019.
[18] Jiang ZT, Qin LL. Low-light image enhancement method based on U-net generative adversarial network. Acta Electronica Sinica,
2020,48(2):258−264 (in Chinese with English abstract).
[19] Jiang ZT, Wu X, Zhang SQ. Low-illumination image enhancement based on MR-VAE. Library Philosophy and Practice, 2019,12:
1−13 (in Chinese with English abstract). http://kns.cnki.net/kcms/detail/11.1826.TP.20191202.1403.002.html
[20] Irwan B, Barret Z, Quoc L, et al. Attention augmented convolutional networks. arXiv preprint arXiv:1904.09925v4, 2019.
3285−3294. [doi: 10.1109/ICCV.2019.00338]