MSSNet: Multi-Scale-Stage Network for Single Image Deblurring

TL;DR

MSSNet is a novel deep learning architecture for single image deblurring that improves upon previous methods by addressing coarse-to-fine scheme defects, achieving state-of-the-art results in quality and efficiency.

Contribution

The paper introduces MSSNet, a multi-scale-stage network with new components that enhance deblurring performance over existing approaches.

Findings

Achieves state-of-the-art deblurring quality

Reduces network size and computation time

Outperforms previous methods in benchmarks

Abstract

Most of traditional single image deblurring methods before deep learning adopt a coarse-to-fine scheme that estimates a sharp image at a coarse scale and progressively refines it at finer scales. While this scheme has also been adopted to several deep learning-based approaches, recently a number of single-scale approaches have been introduced showing superior performance to previous coarse-to-fine approaches both in quality and computation time. In this paper, we revisit the coarse-to-fine scheme, and analyze defects of previous coarse-to-fine approaches that degrade their performance. Based on the analysis, we propose Multi-Scale-Stage Network (MSSNet), a novel deep learning-based approach to single image deblurring that adopts our remedies to the defects. Specifically, MSSNet adopts three novel technical components: stage configuration reflecting blur scales, an inter-scale information propagation scheme, and a pixel-shuffle-based multi-scale scheme. Our experiments show that MSSNet achieves the state-of-the-art performance in terms of quality, network size, and computation time.