Deeply Aggregated Alternating Minimization for Image Restoration
This work addresses image restoration for computer vision applications, presenting an incremental improvement by integrating deep learning into a conventional optimization framework.
The authors tackled image restoration by introducing DeepAM, a framework that trains deep neural networks to enhance steps in the alternating minimization algorithm, resulting in improved performance over recent data-driven and nonlocal-based methods across tasks like denoising and super-resolution.
Regularization-based image restoration has remained an active research topic in computer vision and image processing. It often leverages a guidance signal captured in different fields as an additional cue. In this work, we present a general framework for image restoration, called deeply aggregated alternating minimization (DeepAM). We propose to train deep neural network to advance two of the steps in the conventional AM algorithm: proximal mapping and ?- continuation. Both steps are learned from a large dataset in an end-to-end manner. The proposed framework enables the convolutional neural networks (CNNs) to operate as a prior or regularizer in the AM algorithm. We show that our learned regularizer via deep aggregation outperforms the recent data-driven approaches as well as the nonlocalbased methods. The flexibility and effectiveness of our framework are demonstrated in several image restoration tasks, including single image denoising, RGB-NIR restoration, and depth super-resolution.