TY - GEN
T1 - Multiresolution mixture generative adversarial network for image super-resolution
AU - Wang, Yudiao
AU - Lan, Xuguang
AU - Zhang, Yinshu
AU - Miao, Ruixue
AU - Tian, Zhiqiang
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - With regard to the problem of image super-resolution (SR), generative adversarial network (GAN) can make generated images have more details and better effect on perceptual quality than other methods. However, GAN-based methods may lose the contour of object in some texture-intensive areas. In order to recover contour better and further enhance perceptual quality, we propose a Multiresolution Mixture Generative Adversarial Network for Image Super-Resolution (MRMGAN), which employs a multiresolution mixture network (MRMNet) for image super-resolution. The MRMNet is able to have multiple resolution feature maps at the same time when training. Meanwhile, we propose a residual fluctuation loss, which aims to reduce the overall fluctuation of residual between SR image and high-resolution (HR) image. We evaluated the proposed method on benchmark datasets. Experimental results show that the proposed MRMGAN can get satisfactory performance.
AB - With regard to the problem of image super-resolution (SR), generative adversarial network (GAN) can make generated images have more details and better effect on perceptual quality than other methods. However, GAN-based methods may lose the contour of object in some texture-intensive areas. In order to recover contour better and further enhance perceptual quality, we propose a Multiresolution Mixture Generative Adversarial Network for Image Super-Resolution (MRMGAN), which employs a multiresolution mixture network (MRMNet) for image super-resolution. The MRMNet is able to have multiple resolution feature maps at the same time when training. Meanwhile, we propose a residual fluctuation loss, which aims to reduce the overall fluctuation of residual between SR image and high-resolution (HR) image. We evaluated the proposed method on benchmark datasets. Experimental results show that the proposed MRMGAN can get satisfactory performance.
KW - Generative adversarial network
KW - Multi-resolution mixture network
KW - Residual fluctuation loss
KW - Super-resolution
UR - https://www.scopus.com/pages/publications/85090388867
U2 - 10.1109/ICME46284.2020.9102972
DO - 10.1109/ICME46284.2020.9102972
M3 - 会议稿件
AN - SCOPUS:85090388867
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2020 IEEE International Conference on Multimedia and Expo, ICME 2020
PB - IEEE Computer Society
T2 - 2020 IEEE International Conference on Multimedia and Expo, ICME 2020
Y2 - 6 July 2020 through 10 July 2020
ER -