Extra Proximal-Gradient Inspired Non-local Network
This work addresses image reconstruction for computer vision applications, presenting an incremental improvement by combining optimization algorithms with deep learning techniques.
The authors tackled image reconstruction in inverse problems by proposing a deep network inspired by an accelerated extra proximal gradient algorithm, which incorporates non-local operations and learns nonlinear transforms for sparsity, resulting in outperforming several state-of-the-art deep networks with similar parameter counts.
Variational method and deep learning method are two mainstream powerful approaches to solve inverse problems in computer vision. To take advantages of advanced optimization algorithms and powerful representation ability of deep neural networks, we propose a novel deep network for image reconstruction. The architecture of this network is inspired by our proposed accelerated extra proximal gradient algorithm. It is able to incorporate non-local operation to exploit the non-local self-similarity of the images and to learn the nonlinear transform, under which the solution is sparse. All the parameters in our network are learned from minimizing a loss function. Our experimental results show that our network outperforms several state-of-the-art deep networks with almost the same number of learnable parameter.