当前位置: X-MOL 学术Signal Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hybrid Sparsity Learning for Image Restoration: an Iterative and Trainable Approach
Signal Processing ( IF 3.4 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.sigpro.2020.107751
Fangfang Wu , Weisheng Dong , Tao Huang , Guangming Shi , Shaoyuan Cheng , Xin Li

Abstract State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former class strives to exploit internal prior knowledge about the unknown target images by constructing advanced mathematical models; while the latter class leverages external image prior from a training dataset through powerful neural networks. It is natural to explore their middle ground and pursue a principled approach to learning the hybrid image prior in order to combine the strengths from both worlds. In this paper, we present a systematic approach to achieving this goal called Structured Analysis Sparsity Learning (SASL). Inspired by the strategy of iterative regularization, we propose to learn a hybrid sparse prior from both a collection of reference images (external prior) and the given degraded image (internal prior). Unlike previous hybrid approaches that simply take the average of restored images by different priors, we advocate our approach of combining complementary structured sparse priors in an iterative and trainable manner. By incorporating the knowledge from both domains (internal vs. external), we demonstrate that our iterative and trainable image restoration with a hybrid prior can boost the performance of common tasks including denoising and deblurring. Experimental results show that the proposed SASL image restoration techniques perform comparably with and often better than current state-of-the-art techniques.

中文翻译:

用于图像恢复的混合稀疏学习:一种迭代和可训练的方法

摘要 最先进的图像恢复方法可以分为基于模型和基于学习。前一类力求通过构建高级数学模型来利用未知目标图像的内部先验知识;而后一类通过强大的神经网络利用来自训练数据集的外部图像先验。为了结合两个世界的优势,探索他们的中间立场并采取有原则的方法来先学习混合图像是很自然的。在本文中,我们提出了一种实现这一目标的系统方法,称为结构化分析稀疏学习 (SASL)。受迭代正则化策略的启发,我们建议从参考图像集合(外部先验)和给定退化图像(内部先验)中学习混合稀疏先验。与以前简单地取不同先验恢复图像的平均值的混合方法不同,我们提倡以迭代和可训练的方式组合互补结构稀疏先验的方法。通过结合来自两个领域(内部与外部)的知识,我们证明了使用混合先验的迭代和可训练图像恢复可以提高包括去噪和去模糊在内的常见任务的性能。实验结果表明,所提出的 SASL 图像恢复技术的性能与当前最先进的技术相当并且通常更好。通过结合来自两个领域(内部与外部)的知识,我们证明了使用混合先验的迭代和可训练图像恢复可以提高包括去噪和去模糊在内的常见任务的性能。实验结果表明,所提出的 SASL 图像恢复技术的性能与当前最先进的技术相当并且通常更好。通过结合来自两个领域(内部与外部)的知识,我们证明了使用混合先验的迭代和可训练图像恢复可以提高包括去噪和去模糊在内的常见任务的性能。实验结果表明,所提出的 SASL 图像恢复技术的性能与当前最先进的技术相当并且通常更好。
更新日期:2021-01-01
down
wechat
bug