Lightweight Image Super-Resolution with Information Multi-distillation Network

TL;DR

This paper introduces a lightweight, efficient super-resolution network that effectively handles arbitrary scale factors and real images, outperforming existing methods in quality, memory, and speed.

Contribution

The novel IMDN architecture with multi-distillation blocks and contrast-aware attention improves super-resolution efficiency and flexibility for practical applications.

Findings

Outperforms state-of-the-art SR methods in visual quality.

Reduces memory footprint and inference time.

Handles arbitrary scale factors with an adaptive cropping strategy.

Abstract

In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results. Thanks to the powerful representation capabilities of the deep networks, numerous previous ways can learn the complex non-linear mapping between low-resolution (LR) image patches and their high-resolution (HR) versions. However, excessive convolutions will limit the application of super-resolution technology in low computing power devices. Besides, super-resolution of any arbitrary scale factor is a critical issue in practical applications, which has not been well solved in the previous approaches. To address these issues, we propose a lightweight information multi-distillation network (IMDN) by constructing the cascaded information multi-distillation blocks (IMDB), which contains distillation and selective fusion parts. Specifically, the distillation module extracts hierarchical features step-by-step, and fusion module aggregates them according to the importance of candidate features, which is evaluated by the proposed contrast-aware channel attention mechanism. To process real images with any sizes, we develop an adaptive cropping strategy (ACS) to super-resolve block-wise image patches using the same well-trained model. Extensive experiments suggest that the proposed method performs favorably against the state-of-the-art SR algorithms in term of visual quality, memory footprint, and inference time. Code is available at \url{https://github.com/Zheng222/IMDN}.