Speeding up scaled gradient projection methods using deep neural networks for inverse problems in image processing
Speeding up scaled gradient projection methods using deep neural networks for inverse problems in image processing
复制标题
DOI：
--
复制
发表时间：
2019-02
期刊：
影响因子：
--
通讯作者：
Byung Hyun Lee;S. Chun
中科院分区：
文献类型：
--
作者：
Byung Hyun Lee;S. Chun
传统的基于最优化的方法利用具有图像先验的正演模型来求解图像处理中的反问题。近年来，深度神经网络(DNN)被研究用来显著改善反问题解的图像质量。大多数基于DNN的反问题都集中在使用具有海量数据的数据驱动图像先验。然而，这些方法往往没有继承传统方法的良好性质，使用单调、全局收敛等理论上站得住脚的优化算法。在这里，我们研究了将DNN用于图像处理中反问题的另一种可能性。我们提出了使用DNN的方法来无缝地加快传统基于优化的方法的收敛速度。我们的DNN结合的比例梯度投影方法在不破坏理论性质的情况下，在实践中显著提高了收敛速度，超过了ISTA或FISTA等最先进的传统优化方法，用于图像修复、部分傅立叶样本压缩图像恢复、图像去模糊和稀疏视图投影的医学图像重建等逆问题。
Conventional optimization based methods have utilized forward models with image priors to solve inverse problems in image processing. Recently, deep neural networks (DNN) have been investigated to significantly improve the image quality of the solution for inverse problems. Most DNN based inverse problems have focused on using data-driven image priors with massive amount of data. However, these methods often do not inherit nice properties of conventional approaches using theoretically well-grounded optimization algorithms such as monotone, global convergence. Here we investigate another possibility of using DNN for inverse problems in image processing. We propose methods to use DNNs to seamlessly speed up convergence rates of conventional optimization based methods. Our DNN-incorporated scaled gradient projection methods, without breaking theoretical properties, significantly improved convergence speed over state-of-the-art conventional optimization methods such as ISTA or FISTA in practice for inverse problems such as image inpainting, compressive image recovery with partial Fourier samples, image deblurring, and medical image reconstruction with sparse-view projections.