External and internal learning for single-image super-resolution
External and internal learning for single-image super-resolution
复制标题
DOI：
10.1109/icip.2015.7350773
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Shuang Wang;Shaopeng Lin;Xuefeng Liang;Bo Yue;L. Jiao
中科院分区：
文献类型：
--
作者：
Shuang Wang;Shaopeng Lin;Xuefeng Liang;Bo Yue;L. Jiao
超分辨率（SR）问题仍然面临着明智地利用不同的学习先验来恢复低分辨率图像中丢失的细节的挑战。在这项工作中，我们提出了一种使用低秩分解的新方法，该方法集成了从外部和内部学习中学到的不同先验来构建 SR 图像。该方法首先应用外部字典学习来获取图像之间共同共享的元细节，然后引入内部先验学习来学习图像中共享的局部自相似性（局部结构）。对于 SR 图像构建来说，两者都是必不可少的但不同的先验。利用这些先验，获得了一组初步的 HR 图像，但存在估计误差和噪声。为了抑制误差和噪声，我们将这些HR图像视为降维问题中的高维数据，并使用低秩分解来解决它。实验结果表明，所提出的方法有效地保留了图像细节，在视觉和定量评估方面也优于最先进的方法，特别是在处理噪声方面。
Super-resolution (SR) problem still faces a challenge of wisely utilizing diverse learned priors to recover the lost details in low resolution images. In this work, we propose a novel method using low rank decomposition which integrates diverse priors learned from external and internal learning to construct SR image. The proposed method first applies an external dictionary learning to get the meta-detail that is commonly shared among images, and then introduces an internal prior learning to learn the local self-similarity (local structure) that is shared in the image. Both are essential but different priors for SR image construction. With these priors, a bank of preliminary HR images are obtained but with estimation errors and noise. To restrain the errors and noise, we consider these HR images as a high dimension data in dimension reduction problem, and solve it using a low rank decomposition. Experimental results show the proposed method preserves image details effectively, also outperforms state-of-the-arts in both visual and quantitative assessments, especially in dealing with the noise.