Robust Single Image Super-Resolution via Deep Networks With Sparse Prior
Robust Single Image Super-Resolution via Deep Networks With Sparse Prior
复制标题
DOI：
10.1109/tip.2016.2564643
复制
发表时间：
2016-07-01
影响因子：
10.6
通讯作者：
Huang, Thomas S.
中科院分区：
文献类型：
--
作者：
Liu, Ding;Wang, Zhaowen;Huang, Thomas S.
单图像超分辨率问题是一个不适定问题，它试图从低分辨率观测中恢复高分辨率图像。为了正则化问题的解决方案，以前的方法专注于为自然图像设计良好的先验，例如稀疏表示，或者直接从具有模型的大型数据集中学习先验，例如深度神经网络。在本文中，我们认为传统稀疏编码模型的领域专业知识可以与深度学习的关键成分相结合，以实现进一步改进的结果。我们证明了一个稀疏编码模型，特别是设计用于SR可以体现为一个神经网络的优点，端到端的优化训练数据。该网络具有级联结构，这提高了SR性能的固定和增量缩放因子。所提出的训练和测试方案可以扩展用于具有额外退化（例如噪声和模糊）的图像的鲁棒处理。进行主观评估和分析，以彻底评估各种SR技术。我们提出的模型在广泛的图像上进行了测试，它在定量和感知上都明显优于现有的各种缩放因子的最先进的方法。
Single image super-resolution (SR) is an ill-posed problem, which tries to recover a high-resolution image from its low-resolution observation. To regularize the solution of the problem, previous methods have focused on designing good priors for natural images, such as sparse representation, or directly learning the priors from a large data set with models, such as deep neural networks. In this paper, we argue that domain expertise from the conventional sparse coding model can be combined with the key ingredients of deep learning to achieve further improved results. We demonstrate that a sparse coding model particularly designed for SR can be incarnated as a neural network with the merit of end-to-end optimization over training data. The network has a cascaded structure, which boosts the SR performance for both fixed and incremental scaling factors. The proposed training and testing schemes can be extended for robust handling of images with additional degradation, such as noise and blurring. A subjective assessment is conducted and analyzed in order to thoroughly evaluate various SR techniques. Our proposed model is tested on a wide range of images, and it significantly outperforms the existing state-of-the-art methods for various scaling factors both quantitatively and perceptually.