Single-image translation based on multi-scale dense feature fusion

被引：0
|
作者：
Li Q. [1 ]
Feng L. [1 ]
Yang Q. [1 ]
Wang Y. [2 ]
Geng G. [1 ]
机构：
[1] School of Information Science and Technology, Northwest University, Xi'an
[2] School of Mathematics, Northwest University, Xi'an
来源：
Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2022年 / 30卷 / 10期
关键词：
Dense feature fusion; GAN; Image style transfer; Multi-scale structure; Single-image translation;
D O I：
10.37188/OPE.20223010.1217
中图分类号：
学科分类号：
摘要：
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. © 2022, Science Press. All right reserved.
引用
收藏
页码：1217 / 1227
页数：10
相关论文
共 23 条
  • [1] LV X Q, WU L, GU Y, Et al., Detection of low dose CT pulmonary nodules based on 3D convolution neural network, Opt. Precision Eng, 26, 5, pp. 1211-1218, (2018)
  • [2] KIM J, LEE J K, LEE K M., Accurate image super-resolution using very deep convolutional networks, 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2730, pp. 1646-1654, (2016)
  • [3] ZHANG R, ISOLA P, EFROS A A., Colorful image colorization, Computer Vision-ECCV, 2016, pp. 649-666, (2016)
  • [4] DU Z L, SHEN H Y, SONG G M, Et al., Image style transfer based on improved CycleGAN, Opt. Precision Eng, 27, 8, pp. 1836-1844, (2019)
  • [5] PARK T, EFROS A A, ZHANG R, Et al., Contrastive learning for unpaired image-to-image translation, Computer Vision-ECCV 2020, 2020, pp. 319-345
  • [6] LI Y, LIU X Y, ZHANG H Q, Et al., Optical remote sensing image retrieval based on convolutional neural networks, Opt. Precision Eng, 26, 1, pp. 200-207, (2018)
  • [7] GOODFELLOW I, POUGET A J, MIRZA M, Et al., Generative adversarial nets, Advances in neural information processing systems, (2014)
  • [8] 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, pp. 2242-2251, (2017)
  • [9] KIM T, CHA M, KIM H, Et al., Learning to discover cross-domain relations with generative adversarial networks, International Conference on Machine Learning, pp. 1857-1865, (2017)
  • [10] 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, pp. 2868-2876, (2017)
123