计算机科学
人工智能
核(代数)
图像(数学)
无监督学习
图像翻译
噪音(视频)
模式识别(心理学)
深度学习
翻译(生物学)
超分辨率
数学
组合数学
信使核糖核酸
基因
生物化学
化学
作者
Yuan Yuan,Siyuan Liu,Jiawei Zhang,Yongbing Zhang,Chao Dong,Lin Li
标识
DOI:10.1109/cvprw.2018.00113
摘要
We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the low-resolution input is further degraded by noises and blurring. This complicated setting makes supervised learning and accurate kernel estimation impossible. To solve this problem, we resort to unsupervised learning without paired data, inspired by the recent successful image-to-image translation applications. With generative adversarial networks (GAN) as the basic component, we propose a Cycle-in-Cycle network structure to tackle the problem within three steps. First, the noisy and blurry input is mapped to a noise-free low-resolution space. Then the intermediate image is up-sampled with a pre-trained deep model. Finally, we fine-tune the two modules in an end-to-end manner to get the high-resolution output. Experiments on NTIRE2018 datasets demonstrate that the proposed unsupervised method achieves comparable results as the state-of-the-art supervised models.
科研通智能强力驱动
Strongly Powered by AbleSci AI