Functional Neural Networks for Parametric Image Restoration Problems

TL;DR

This paper introduces FuncNet, a novel neural network architecture that efficiently and effectively handles parametric image restoration tasks by modeling parameters as functions, outperforming existing methods across super-resolution, denoising, and JPEG deblocking.

Contribution

The paper proposes FuncNet, a new neural network framework that models parameters as functions, enabling a single model to handle multiple levels of image restoration parameters.

Findings

FuncNet outperforms state-of-the-art methods in super-resolution.

FuncNet achieves superior results in image denoising.

FuncNet is effective across multiple parametric image restoration tasks.

Abstract

Almost every single image restoration problem has a closely related parameter, such as the scale factor in super-resolution, the noise level in image denoising, and the quality factor in JPEG deblocking. Although recent studies on image restoration problems have achieved great success due to the development of deep neural networks, they handle the parameter involved in an unsophisticated way. Most previous researchers either treat problems with different parameter levels as independent tasks, and train a specific model for each parameter level; or simply ignore the parameter, and train a single model for all parameter levels. The two popular approaches have their own shortcomings. The former is inefficient in computing and the latter is ineffective in performance. In this work, we propose a novel system called functional neural network (FuncNet) to solve a parametric image restoration problem with a single model. Unlike a plain neural network, the smallest conceptual element of our FuncNet is no longer a floating-point variable, but a function of the parameter of the problem. This feature makes it both efficient and effective for a parametric problem. We apply FuncNet to super-resolution, image denoising, and JPEG deblocking. The experimental results show the superiority of our FuncNet on all three parametric image restoration tasks over the state of the arts.