浏览全部资源
扫码关注微信
1.西北大学 信息科学与技术学院,陕西 西安 710127
2.西北大学 数学学院,陕西 西安 710127
Received:22 December 2021,
Revised:18 January 2022,
Published:25 May 2022
移动端阅览
李启航,冯龙,杨清等.基于多尺度密集特征融合的单图像翻译[J].光学精密工程,2022,30(10):1217-1227.
LI Qihang,FENG Long,YANG Qing,et al.Single-image translation based on multi-scale dense feature fusion[J].Optics and Precision Engineering,2022,30(10):1217-1227.
李启航,冯龙,杨清等.基于多尺度密集特征融合的单图像翻译[J].光学精密工程,2022,30(10):1217-1227. DOI: 10.37188/OPE.20223010.1217.
LI Qihang,FENG Long,YANG Qing,et al.Single-image translation based on multi-scale dense feature fusion[J].Optics and Precision Engineering,2022,30(10):1217-1227. DOI: 10.37188/OPE.20223010.1217.
为了解决现有的单图像翻译模型生成的图像质量低、细节特征差的问题,本文提出了基于多尺度密集特征融合的单图像翻译模型。该模型首先借用多尺度金字塔结构思想,对原图像和目标图像进行下采样,得到不同尺寸的输入图像。然后在生成器中将不同尺寸的图像输入到密集特征模块进行风格特征提取,将提取到的风格特征从原图像迁移到目标图像中,通过与判别器不断的博弈对抗,生成所需要的翻译图像;最后,本文通过渐进式增长生成器训练的方式,在训练的每个阶段中不断增加密集特征模块,实现生成图像从全局风格到局部风格的迁移,生成所需要的翻译图像。本文在各种无监督图像到图像翻译任务上进行了广泛的实验,实验结果表明,与现有的方法相比,本文的方法训练时长缩短了75%,并且生成图像的SIFID值平均降低了22.18%。本文的模型可以更好地捕获源域和目标域之间分布的差异,提高图像翻译的质量。
To solve the problems of low image quality and poor detail features generated by the existing single image translation models, a single image translation model based on multi-scale dense feature fusion is proposed in this paper. First, in this model, the idea of multi-scale pyramid structure is used to downsample the original and target images to obtain input images of different sizes. Then, in the generator, images of different sizes are input into the dense feature module for style feature extraction, which are transferred from the original image to the target image, and the required translation image is generated through continuous game confrontation with the discriminator. Finally, dense feature modules are added in each stage of training by means of incremental growth generator training, which realizes the migration of generated images from global to local styles, and generates the required translation images. Extensive experiments have been conducted on various unsupervised images to perform image translation tasks. The experimental results demonstrate that in contrast to the existing methods, the training time of this method is shortened by 80%, and the SIFID value of the generated image is reduced by 22.18%. Therefore, the model proposed in this paper can better capture the distribution difference between the source and target domains, and improve the quality of image translation.
吕晓琪 , 吴凉 , 谷宇 , 等 . 基于三维卷积神经网络的低剂量CT肺结节检测 [J]. 光学 精密工程 , 2018 , 26 ( 5 ): 1211 - 1218 . doi: 10.3788/OPE.20182605.1211 http://dx.doi.org/10.3788/OPE.20182605.1211
LV X Q , WU L , GU Y , et al . Detection of low dose CT pulmonary nodules based on 3D convolution neural network [J]. Opt. Precision Eng. , 2018 , 26 ( 5 ): 1211 - 1218 . (in Chinese) . doi: 10.3788/OPE.20182605.1211 http://dx.doi.org/10.3788/OPE.20182605.1211
KIM J , LEE J K , LEE K M . Accurate image super-resolution using very deep convolutional networks [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition . 2730,2016 , Las Vegas, NV, USA . IEEE , 2016 : 1646 - 1654 . doi: 10.1109/cvpr.2016.182 http://dx.doi.org/10.1109/cvpr.2016.182
ZHANG R , ISOLA P , EFROS A A . Colorful image colorization [C]. Computer Vision-ECCV 2016 , 2016 : 649 - 666 . doi: 10.1007/978-3-319-46487-9_40 http://dx.doi.org/10.1007/978-3-319-46487-9_40
杜振龙 , 沈海洋 , 宋国美 , 等 . 基于改进CycleGAN的图像风格迁移 [J]. 光学 精密工程 , 2019 , 27 ( 8 ): 1836 - 1844 . doi: 10.3788/ope.20192708.1836 http://dx.doi.org/10.3788/ope.20192708.1836
DU Z L , SHEN H Y , SONG G M , et al . Image style transfer based on improved CycleGAN [J]. Opt. Precision Eng. , 2019 , 27 ( 8 ): 1836 - 1844 . (in Chinese) . doi: 10.3788/ope.20192708.1836 http://dx.doi.org/10.3788/ope.20192708.1836
PARK T , EFROS A A , ZHANG R , et al . Contrastive learning for unpaired image-to-image translation [C]. Computer Vision-ECCV 2020 , 2020 : 319 - 345 . doi: 10.1007/978-3-030-58545-7_19 http://dx.doi.org/10.1007/978-3-030-58545-7_19
李宇 , 刘雪莹 , 张洪群 , 等 . 基于卷积神经网络的光学遥感图像检索 [J]. 光学 精密工程 , 2018 , 26 ( 1 ): 200 - 207 . doi: 10.3788/OPE.20182601.0200 http://dx.doi.org/10.3788/OPE.20182601.0200
LI Y , LIU X Y , ZHANG H Q , et al . Optical remote sensing image retrieval based on convolutional neural networks [J]. Opt. Precision Eng. , 2018 , 26 ( 1 ): 200 - 207 . (in Chinese) . doi: 10.3788/OPE.20182601.0200 http://dx.doi.org/10.3788/OPE.20182601.0200
GOODFELLOW I , POUGET A J , MIRZA M , et al . Generative adversarial nets [J]. Advances in neural information processing systems , 2014 , 27 .
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 . 2229,2017 , Venice, Italy . IEEE , 2017 : 2242 - 2251 . doi: 10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244
KIM T , CHA M , KIM H , et al . Learning to discover cross-domain relations with generative adversarial networks [C]. International Conference on Machine Learning. PMLR , 2017 : 1857- 1865 .. doi: 10.1109/iccvw.2017.229 http://dx.doi.org/10.1109/iccvw.2017.229
YI Z L , ZHANG H , TAN P , et al . DualGAN: unsupervised dual learning for image-to-image translation [C]. 2017 IEEE International Conference on Computer Vision . 2229,2017 , Venice, Italy . IEEE , 2017 : 2868 - 2876 . doi: 10.1109/iccv.2017.310 http://dx.doi.org/10.1109/iccv.2017.310
SHAHAM T R , DEKEL T , MICHAELI T . SinGAN: learning a generative model from a single natural image [C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). 272,2019 , Seoul, Korea (South). IEEE , 2019 : 4569 - 4579 . doi: 10.1109/iccv.2019.00467 http://dx.doi.org/10.1109/iccv.2019.00467
LIN J X , PANG Y X , XIA Y C , et al . TuiGAN: learning versatile image-to-image translation with two unpaired images [C]. Computer Vision-ECCV 2020 , 2020 : 18 - 35 . doi: 10.1007/978-3-030-58548-8_2 http://dx.doi.org/10.1007/978-3-030-58548-8_2
HUANG G , LIU Z , MAATEN LVAN DER , et al . Densely connected convolutional networks [C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition . 2126,2017 , Honolulu, HI, USA . IEEE , 2017 : 2261 - 2269 . doi: 10.1109/cvpr.2017.243 http://dx.doi.org/10.1109/cvpr.2017.243
KARRAS T , AILA , LAINE S , et al . Progressive growing of GANs for improved quality, stability, and variation [EB/OL]. 2017: arXiv : 1710 .10196[cs.NE]. https://arxiv.org/abs/1710.10196 https://arxiv.org/abs/1710.10196
HINZ T , FISHER M , WANG O , et al . Improved techniques for training single-image GANs [C]. 2021 IEEE Winter Conference on Applications of Computer Vision . 38,2021 , Waikoloa , HI, USA . IEEE , 2021 : 1299 - 1308 . doi: 10.1109/wacv48630.2021.00134 http://dx.doi.org/10.1109/wacv48630.2021.00134
ZHENG C X , CHAM T J , CAI J F . The spatially-correlative loss for various image translation tasks [C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025,2021 , Nashville, TN, USA. IEEE , 2021 : 16402 - 16412 . doi: 10.1109/cvpr46437.2021.01614 http://dx.doi.org/10.1109/cvpr46437.2021.01614
LEE H Y , TSENG H Y , HUANG J B , et al . Diverse image-to-image translation via disentangled representations [C]. Computer Vision-ECCV 2018 , 2018 : 35 - 51 . doi: 10.1007/978-3-030-01246-5_3 http://dx.doi.org/10.1007/978-3-030-01246-5_3
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition . 2730,2016 , Las Vegas, NV, USA . IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
GULRAJANI I , AHMED F , ARJOVSKY M , et al . Improved training of wasserstein gans [J]. arXiv preprint arXiv: 1704.00028 , 2017 .
PUMAROLA A , AGUDO A , MARTINEZ A M , et al . GANimation: anatomically-aware facial animation from a single image [J]. Computer Vision-ECCV:European Conference on Computer Vision: Proceedings European Conference on Computer Vision , 2018 , 11214 : 835 - 851 . doi: 10.1007/978-3-030-01249-6_50 http://dx.doi.org/10.1007/978-3-030-01249-6_50
HEUSEL M , RAMSAUER H , UNTERTHINER T , et al . GANs trained by a two time-scale update rule converge to a local Nash equilibrium [J]. Advances in neural information processing systems , 2017 . doi: 10.48550/arXiv.1706.08500 http://dx.doi.org/10.48550/arXiv.1706.08500
NEWEY W K . Adaptive estimation of regression models via moment restrictions [J]. Journal of Econometrics , 1988 , 38 ( 3 ): 301 - 339 . doi: 10.1016/0304-4076(88)90048-6 http://dx.doi.org/10.1016/0304-4076(88)90048-6
DEMIR U , UNAL G . Patch-based image inpainting with generative adversarial networks [EB/OL]. 2018: arXiv : 1803 .07422[cs.CV]. https://arxiv.org/abs/1803.07422 https://arxiv.org/abs/1803.07422
0
Views
611
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution