Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding

TL;DR

This paper introduces BMDSRNet, a novel neural network that simultaneously performs deblurring and super-resolution on static images by learning dynamic spatio-temporal features, outperforming existing methods.

Contribution

The paper presents BMDSRNet, a new approach that learns from single motion-blurred images to achieve both deblurring and super-resolution, addressing limitations of prior multi-frame methods.

Findings

BMDSRNet outperforms recent state-of-the-art methods.

It effectively handles both deblurring and super-resolution tasks.

The network learns bidirectional spatio-temporal information from static images.

Abstract

Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Single-Image SR generally handles each image independently, but ignores the temporal information implied in continuing frames. Multi-frame SR is able to model the temporal dependency via capturing motion information. However, it relies on neighbouring frames which are not always available in the real world. Meanwhile, slight camera shake easily causes heavy motion blur on long-distance-shot low-resolution images. To address these problems, a Blind Motion Deblurring Super-Reslution Networks, BMDSRNet, is proposed to learn dynamic spatio-temporal information from single static motion-blurred images. Motion-blurred images are the accumulation over time during the exposure of cameras, while the proposed BMDSRNet learns the reverse process and uses three-streams to learn Bidirectional spatio-temporal information based on well designed reconstruction loss functions to recover clean high-resolution images. Extensive experiments demonstrate that the proposed BMDSRNet outperforms recent state-of-the-art methods, and has the ability to simultaneously deal with image deblurring and SR.