Deep Non-Blind Deconvolution Via Generalized Low-Rank Approximation

Authors:
Wenqi Ren Chinese Academy of Sciences
Jiawei Zhang Sensetime Research
Lin Ma Tencent AI Lab
Jinshan Pan Nanjing University of Science and Technology
Xiaochun Cao Chinese Academy of Sciences
Wangmeng Zuo Harbin Institute of Technology
Wei Liu Tencent AI Lab
Ming-Hsuan Yang UC Merced / Google

Introduction:

In this paper, the authors present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.

Abstract:

In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework. The proposed neural network is motivated by the low-rank property of pseudo-inverse kernels. We first compute a generalized low-rank approximation for a large number of blur kernels, and then use separable filters to initialize the convolutional parameters in the network. Our analysis shows that the estimated decomposed matrices contain the most essential information of the input kernel, which ensures the proposed network to handle various blurs in a unified framework and generate high-quality deblurring results. Experimental results on benchmark datasets with noise and saturated pixels demonstrate that the proposed algorithm performs favorably against state-of-the-art methods.

You may want to know: