Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

TL;DR

This paper introduces a deep convolutional auto-encoder with symmetric skip connections for image restoration tasks, improving training efficiency and restoration quality.

Contribution

It proposes a novel deep auto-encoder architecture with symmetric skip connections that enhances training speed and restoration performance.

Findings

Faster convergence during training

Improved image restoration quality

Effective handling of deep network training issues

Abstract

Image restoration, including image denoising, super resolution, inpainting, and so on, is a well-studied problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers. In other words, the network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers capture the abstraction of image contents while eliminating corruptions. Deconvolutional layers have the capability to upsample the feature maps and recover the image details. To deal with the problem that deeper networks tend to be more difficult to train, we propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains better results.