Feature Constraint CycleGAN for Single Image Dehazing Algorithm

Dianwei Wang; Shunli Li; Pengfei Han; Ying Liu; Jing Jiang; Xincheng Ren

doi:10.3788/LOP202158.1410017

[1] Wang D W, Han P F, Fan J L et al. Multispectral image enhancement based on illuminance-reflection imaging model and morphology operation[J]. Acta Physica Sinica, 67, 210701(2018).

[2] Zhong W F, Yuan D X. Low-illumination-based enhancement algorithm of color images with fog[J]. Laser & Optoelectronics Progress, 57, 161021(2020).

[3] Zheng Y, Gao Q, Wang D et al. Image-dehazing method based on improved dynamic atmospheric scattering coefficient function[J]. Laser & Optoelectronics Progress, 57, 181003(2020).

[4] Wang Z D, Jing X, Sun G D et al. Image dehazing of dark channels based on area contrast constraint[J]. Chinese Journal of Lasers, 46, 0810003(2019).

[5] He K M, Sun J, Tang X O et al. Single image haze removal using dark channel prior[C]. // IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami Beach, FL., 1956-1963(2009).

[6] Zhu Q S, Mai J M, Shao L. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing, 24, 3522-3533(2015).

[7] Cai B L, Xu X M, Jia K et al. DehazeNet: an end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing, 25, 5187-5198(2016). http://www.tandfonline.com/servlet/linkout?suffix=cit0033&dbid=8&doi=10.1080%2F02564602.2016.1276868&key=28873058

[8] Ren W Q, Liu S, Zhang H et al. Single image dehazing via multi-scale convolutional neural networks[C]. //Leibe B, Matas J, Sebe N, et al. ECCV 2016: computer vision-ECCV 2016, 154-169(2016).

[9] Chen Y, Guo H G, Ai Y P. Single image dehazing method based on multi-scale convolution neural network[J]. Acta Optica Sinica, 39, 1010001(2019).

[10] Zhu J Y, Park T, Isola P et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]. //2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy., 2242-2251(2017).

[11] Ignatov A, Kobyshev N, Timofte R et al. DSLR-quality photos on mobile devices with deep convolutional networks[EB/OL]. (2017-04-08)[2020-08-20]. https://arxiv.org/abs/1704.02470

[12] Ledig C, Theis L, Huszár F et al. Photo-realistic single image super-resolution using a generative adversarial network[C]. //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA., 105-114(2017).

[13] Abadi M, Agarwal A, Barham P et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems[EB/OL]. (2016-03-16) [2018-04-08]. https://arxiv.org/abs/1603.04467

[14] Ancuti C, Ancuti C O, de Vleeschouwer C. D-HAZY: a dataset to evaluate quantitatively dehazing algorithms[C]. //2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, AZ, USA, 2226-2230(2016).

[15] Silberman N, Hoiem D, Kohli P et al. Indoor segmentation and support inference from RGBD images[C]. //Fitzgibbon A, Lazebnik S, Perona P, et al. ECCV 2012: computer vision-ECCV 2012, 746-760(2012).

[16] Scharstein D, Hirschmüller H, Kitajima Y et al. High-resolution stereo datasets with subpixel-accurate ground truth[M]. //Jiang X Y, Hornegger J, Koch R, et al. GCPR 2014: Pattern Recognition, 31-42(2014).