DeepAI AI Chat
Log In Sign Up

Extra Proximal-Gradient Inspired Non-local Network

by   Qingchao Zhang, et al.
University of Florida

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.


page 5

page 9

page 10


Non-Local Color Image Denoising with Convolutional Neural Networks

We propose a novel deep network architecture for grayscale and color ima...

Self-Convolution: A Highly-Efficient Operator for Non-Local Image Restoration

Constructing effective image priors is critical to solving ill-posed inv...

Image Compressed Sensing Using Non-local Neural Network

Deep network-based image Compressed Sensing (CS) has attracted much atte...

Deep Graph-Convolutional Image Denoising

Non-local self-similarity is well-known to be an effective prior for the...

A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems

Optimization algorithms for solving nonconvex inverse problem have attra...

CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion

Label propagation is a popular technique for anatomical segmentation. In...

Jigsaw Puzzle Solving Using Local Feature Co-Occurrences in Deep Neural Networks

Archaeologists are in dire need of automated object reconstruction metho...