Can fully convolutional networks perform well for general image restoration problems?

TL;DR

This paper explores the use of fully convolutional networks for image restoration tasks, demonstrating their effectiveness in denoising and inpainting, and outperforming traditional methods.

Contribution

It introduces a novel FCN-based approach for low-level image restoration, adapting high-level vision network architectures for this purpose.

Findings

Outperforms traditional sparse coding methods in denoising

Achieves competitive results with state-of-the-art restoration techniques

Successfully handles blind image inpainting with high visual quality

Abstract

We present a fully convolutional network(FCN) based approach for color image restoration. FCNs have recently shown remarkable performance for high-level vision problem like semantic segmentation. In this paper, we investigate if FCN models can show promising performance for low-level problems like image restoration as well. We propose a fully convolutional model, that learns a direct end-to-end mapping between the corrupted images as input and the desired clean images as output. Our proposed method takes inspiration from domain transformation techniques but presents a data-driven task specific approach where filters for novel basis projection, task dependent coefficient alterations, and image reconstruction are represented as convolutional networks. Experimental results show that our FCN model outperforms traditional sparse coding based methods and demonstrates competitive performance compared to the state-of-the-art methods for image denoising. We further show that our proposed model can solve the difficult problem of blind image inpainting and can produce reconstructed images of impressive visual quality.