In order to solve the problems of color distortion, semantic ambiguity, unclear texture and shape characteristics in the process of near-infrared image colorization, we propose a method of infrared image colorization (RAUGAN) . Firstly, the CycleGAN network generator is improved, and a Res-ASPP-UNet network is designed and fused, which connects atrous spatial pyramid pooling(ASPP) to Skip connection structure of the original UNet, the output characteristic graphs of different scales in the decoding branch can be combined with the corresponding output characteristic graphs in the encoder. Secondly, a deep bottleneck layer composed of residual block, convolutional block attention module (CBAM) is designed to replace the bottleneck layer in UNET network to enhance the local area feature, improve its recognition ability and prevent gradient explosion. Finally, the perceptual loss function is introduced in the discriminant network to solve the problem of color restoration distortion.Experimental results show that the proposed method is superior to the original CycleGAN network.
ReinhardE, AdhikhminM, GoochB, et al. Color transfer between images[J]. IEEE Computer Graphics and Applications, 2001, 21(5): 34-41.
[2]
WelshT, AshikhminM, MuellerK. Transferring color to greyscale images[J]. ACM Transactions on Graphics, 2002, 21(3): 277-280.
[3]
LevinA, LischinskiD, WeissY. Colorization using optimization[J]. ACM Transactions on Graphics, 2004, 23(3): 689-694.
[4]
GoodfellowI J, PougetA J, MirzaM, et al.Generative adversarial nets[C]∥Advances in Neural Information Processing Systems, Montréal, Canada, 2014:2672-2680.
[5]
IsolaP, ZhuJ, ZhouT, et al. Image-to-image translation with conditional adversarial networks[C]∥Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition, Las Vegas, USA, 2016: 1125-1134.
[6]
ParkT, LiuM Y, WangT C, et al. Semantic imagesynthesis with spatially-adaptive normalization[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 2337-2346.
[7]
WangT C, LiuM Y, ZhuJ Y, et al. High-resolutionimage synthesis and semantic manipulation withconditional gans[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 8798-8807.
[8]
HuangX, LiuM Y, BelongieS, et al. Multimodal unsupervised image-to-image translation[C]∥Proceedings of the European Conference on Computer Vision, Munichi, Germany, 2018:172-189.
[9]
LeeH Y, TsengH Y, HuangJ B, et al. Diverse image-to-image translation via disentangled representations[C]∥Proceedings of the European Conference on Computer Vision, Munichi, Germany, 2019:35-51.
[10]
YiZ, ZhangH, TanP, et al. Dualgan: unsupervised dual learning for image-to-image translation[C]∥Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2849-2857.
[11]
SuárezP L, SappaA D, VintimillaB X. Infrared image colorization based on a triplet dcgan architecture[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, 2017: 212-217.
WangXiao-yu. Research on image colorization algorithm based on color migration[D]. Changchun: School of Electronic and Information Engineering, Changchun University of Science and Technology, 2020.
[14]
LiS, HanB F, YuZ J, et al. I2VGAN:unpaired Infrared to-visible video translation[C]∥Proceedings of the 29th ACM International Conference on Multimedia, New York,USA, 2021:3061-3069.
GaoMei-ling, DuanJin, MoSu-xin, et al. Near infrared image colorization method based on dilated-cycle convolution[J]. Optical Technique, 2022, 48(6): 742-748.
[17]
ChenJ, ChenJ, ChaoH, et al. Image blind denoising with generative adversarial network based noise modeling[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018:3155-3164.
WangXiao-yu, HuXin-hao, HanChang-lin. Face pencil drawing algorithms based on generative adversarial network[J]. Journal of Jilin University (Engineering nd Technology Edition), 2021, 51(1): 285-292.
[22]
MondayH N, LiJ, NnejiG U, et al. A wavelet convolutional capsule network with modified super resolution generative adversarial network for fault diagnosis and classification[J]. Complex & Intelligent Systems, 2022, 8: 4831-4847.
PengYan-fei, ZhangPing-jia, GaoYi, et al. Attention fusion generative adversarial network for single-image super-resolution reconstruction[J]. Laser &Optoelectronics Progress, 2021, 58(20): 182-191.
[25]
LiangC C, GeorgeP, IasonasK, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[26]
WooS, ParkJ, LeeJ Y, et al. CBAM: convolutional block attention module[C]∥Proceedings of the 15thEurope an Conference on Computer Visdom, Munich, Germany, 2018: 3-19.
[27]
LiC, WanD M. Precomputed real-time texture synthesis with markovian generative adversarial networks[C]∥European Conference on Computer Vision of IEEE, Amsterdam, The Netherlands, 2016:702-716.
[28]
WangS, ParkJ, KimN, et al. Multispectral pedestrian detection: benchmark dataset and baseline[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 1037-1045.
[29]
ParkT, LiuM Y, WangT C, et al. Semantic image synthesis with spatially-adaptive normalization[J]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019:2337-2346.
[30]
ZhuJ Y, ParkT, IsolaP, et al. Unpaired image-to-image translation using cycle-consistent adversarial network[C]∥IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2223-2232.
[31]
KancharaguntaB K, RamS D. CDGAN: cyclic discriminative generative adversarial networks forimage-to-image transformation[J]. Journal of Visual Communication and Image Representation, 2022, 82:103382.