Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution
This addresses image restoration for computer vision applications, but appears incremental as it builds on existing iterative frameworks with network-based priors.
The paper tackles the problem of non-blind deconvolution by proposing a fully convolutional network that decomposes it into denoising and deconvolution steps, achieving favorable performance against state-of-the-art methods in quality and speed on benchmark datasets.
In this paper, we propose a fully convolutional networks for iterative non-blind deconvolution We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noises in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve the blurred images in a multi-stage framework. The proposed method is able to learn an adaptive image prior, which keeps both local (details) and global (structures) information. Both quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of quality and speed.