Image Super-Resolution Via Sparse Representation
Image Super-Resolution Via Sparse Representation
复制标题
DOI：
10.1109/tip.2010.2050625
复制
发表时间：
2010-11-01
影响因子：
10.6
通讯作者：
Ma, Yi
中科院分区：
文献类型：
--
作者：
Yang, Jianchao;Wright, John;Ma, Yi
提出了一种基于稀疏信号表示的单图像超分辨新方法。图像统计的研究表明，图像补丁可以很好地表示为一个稀疏的线性组合的元素从一个适当的选择过完备的字典。受此观察的启发，我们为低分辨率输入的每个补丁寻求稀疏表示，然后使用该表示的系数来生成高分辨率输出。压缩感知的理论结果表明，在温和的条件下，稀疏表示可以正确地恢复从下采样信号。通过为低分辨率和高分辨率图像块联合训练两个字典，我们可以加强低分辨率和高分辨率图像块对之间的稀疏表示相对于它们自己的字典的相似性。因此，低分辨率图像块的稀疏表示可以与高分辨率图像块字典一起应用以生成高分辨率图像块。与以前的方法相比，学习的字典对是补丁对的更紧凑的表示，以前的方法只是对大量的图像补丁对进行采样[1]，大大降低了计算成本。这种稀疏先验的有效性证明了一般的图像超分辨率（SR）和特殊情况下的脸幻觉。在这两种情况下，我们的算法生成的高分辨率图像是有竞争力的，甚至上级的质量比其他类似的SR方法产生的图像。此外，我们的方法的局部稀疏建模是自然鲁棒的噪声，因此，该算法可以处理SR噪声输入在一个更统一的框架。
This paper presents a new approach to single-image superresolution, based upon sparse signal representation. Research on image statistics suggests that image patches can be well-represented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary. Inspired by this observation, we seek a sparse representation for each patch of the low-resolution input, and then use the coefficients of this representation to generate the high-resolution output. Theoretical results from compressed sensing suggest that under mild conditions, the sparse representation can be correctly recovered from the downsampled signals. By jointly training two dictionaries for the low-and high-resolution image patches, we can enforce the similarity of sparse representations between the low-resolution and high-resolution image patch pair with respect to their own dictionaries. Therefore, the sparse representation of a low-resolution image patch can be applied with the high-resolution image patch dictionary to generate a high-resolution image patch. The learned dictionary pair is a more compact representation of the patch pairs, compared to previous approaches, which simply sample a large amount of image patch pairs [1], reducing the computational cost substantially. The effectiveness of such a sparsity prior is demonstrated for both general image super-resolution (SR) and the special case of face hallucination. In both cases, our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. In addition, the local sparse modeling of our approach is naturally robust to noise, and therefore the proposed algorithm can handle SR with noisy inputs in a more unified framework.