Fast and Accurate Single Image Super-Resolution via Information Distillation Network

TL;DR

This paper introduces a compact deep convolutional neural network for single image super-resolution that balances high accuracy with low computational complexity, achieving faster processing while maintaining superior image quality.

Contribution

The paper proposes a novel information distillation network with feature enhancement and compression units, improving efficiency and accuracy over existing super-resolution methods.

Findings

Outperforms state-of-the-art methods in accuracy.

Achieves faster processing times.

Uses fewer filters and group convolution for efficiency.

Abstract

Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution. However, as the depth and width of the networks increase, CNN-based super-resolution methods have been faced with the challenges of computational complexity and memory consumption in practice. In order to solve the above questions, we propose a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image. In general, the proposed model consists of three parts, which are feature extraction block, stacked information distillation blocks and reconstruction block respectively. By combining an enhancement unit with a compression unit into a distillation block, the local long and short-path features can be effectively extracted. Specifically, the proposed enhancement unit mixes together two different types of features and the compression unit distills more useful information for the sequential blocks. In addition, the proposed network has the advantage of fast execution due to the comparatively few numbers of filters per layer and the use of group convolution. Experimental results demonstrate that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.