arrow
返回

Segmentation-aware image super-resolution with generative adversarial networks

delete2025-01-27
delete0
PRE
AI
王
王继良 (Jiliang Wang) *
C
Cancan Jin
DOI:10.1007/s00530-025-01668-xdelete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Deep neural networks have greatly facilitated the research in the area of image super-resolution. Existing super-resolution networks primarily focus on optimizing visual image quality, and there has been little work considering the potential use of the super-resolved image for machine vision tasks, such as semantic segmentation. In this paper, we propose a segmentation-aware image super-resolution network, by incorporating machine-related semantic segmentation task requirement. To achieve this, we propose to generate super-resolved images by employing generative adversarial networks, where the super-resolution network functions as the generator, while the discriminator consists of the popular real/fake classification branch and an additional task branch. With this specially-designed multi-branch discriminator, segmentation task requirement is used as an added training objective provided to the generator for producing super-resolved images with segmentation awareness. Moreover, by performing alternative training between the generator and the discriminator, we dynamically enhance the capacity of task branch along with the super-resolving process, achieving generalization ability for the resulting super-resolved image. Experimental results show that, for the semantic segmentation task, our proposed method is at most 6.8 higher than competing methods in terms of mIoU score. Furthermore, our method can also generate visually better super-resolved images at the same time.
Keyword:
Deep learning
Generative adversarial network
Image super-resolution
Semantic segmentation

期刊

Multimedia Systems 封面图
Multimedia Systems
IF:
3.1
论文数:
2.8K
被引数:
2.7K

机构

H
hunan university
学者数:
4.5W
论文数: 3.3W
被引数: 70
引用论文

引用论文

err
IF0
err
err0
PREAI
err
err分享
err收藏
Dual-Path Deep Fusion Network for Face Image Hallucination
err2022-01-01
err85
PREAI
errJiang, Kui; Wang, Zhongyuan; Yi, Peng; Lu, Tao; Jiang, Junjun; Xiong, Zixiang
err分享
err收藏
Hierarchical dense recursive network for image super-resolution
err2020-11-01
err184
PREAI
errJiang, Kui; Wang, Zhongyuan; Yi, Peng; Jiang, Junjun
err分享
err收藏
err分享
err收藏
学者 查看更多内容