arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1012.1184cs.CVcs.MM
收藏

基于自适应稀疏域选择和自适应正则化的图像去模糊和超分辨率

Image Deblurring and Super-resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

Xidian University(西安电子科技大学);The Hong Kong Polytechnic University(香港理工大学);McMaster University(麦克马斯特大学)

Weisheng Dong, Lei Zhang, Guangming Shi, Xiaolin Wu

摘要:

稀疏表示作为一种强有力的统计图像建模技术,已成功地应用于各种图像复原应用中。稀疏表示的成功归功于l1范数优化技术的发展,以及自然图像在某些领域具有内在稀疏性的事实。图像复原的质量在很大程度上取决于所采用的稀疏域是否能很好地代表底层图像。考虑到不同图像或单个图像中不同块的内容可能会有很大差异,我们建议从预先收集的示例图像块数据集中学习不同的基集,然后对于待处理的给定块,自适应地选择一组基来表征局部稀疏域。我们进一步引入两个自适应正则化项到稀疏表示框架中。首先,从示例图像块的数据集学习一组自回归(AR)模型。自适应地选择最适合给定块的AR模型来正则化图像局部结构。其次,引入图像的非局部自相似性作为正则化项。此外,稀疏正则化参数自适应估计更好的图像复原性能。大量的图像去模糊和超分辨率实验表明,该方法通过自适应稀疏域选择和自适应正则化,在峰值信噪比(PSNR)和视觉感知方面都比现有算法有更好的效果。

英文摘要:

As a powerful statistical image modeling technique, sparse representation has been successfully used in various image restoration applications. The success of sparse representation owes to the development of l1-norm optimization techniques, and the fact that natural images are intrinsically sparse in some domain. The image restoration quality largely depends on whether the employed sparse domain can represent well the underlying image. Considering that the contents can vary significantly across different images or different patches in a single image, we propose to learn various sets of bases from a pre-collected dataset of example image patches, and then for a given patch to be processed, one set of bases are adaptively selected to characterize the local sparse domain. We further introduce two adaptive regularization terms into the sparse representation framework. First, a set of autoregressive (AR) models are learned from the dataset of example image patches. The best fitted AR models to a given patch are adaptively selected to regularize the image local structures. Second, the image non-local self-similarity is introduced as another regularization term. In addition, the sparsity regularization parameter is adaptively estimated for better image restoration performance. Extensive experiments on image deblurring and super-resolution validate that by using adaptive sparse domain selection and adaptive regularization, the proposed method achieves much better results than many state-of-the-art algorithms in terms of both PSNR and visual perception.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑