Generalizing Event-Based Motion Deblurring in Real-World Scenarios

TL;DR

This paper introduces a scale-aware, self-supervised learning approach for event-based motion deblurring that generalizes to real-world scenarios with varying spatial and temporal scales, supported by a new dataset.

Contribution

It proposes a novel scale-aware network and self-supervised scheme to improve real-world event-based deblurring performance across diverse conditions.

Findings

Achieves superior deblurring results on real-world data

Effectively handles multi-scale motion blur

Introduces a new dataset for event-based deblurring research

Abstract

Event-based motion deblurring has shown promising results by exploiting low-latency events. However, current approaches are limited in their practical usage, as they assume the same spatial resolution of inputs and specific blurriness distributions. This work addresses these limitations and aims to generalize the performance of event-based deblurring in real-world scenarios. We propose a scale-aware network that allows flexible input spatial scales and enables learning from different temporal scales of motion blur. A two-stage self-supervised learning scheme is then developed to fit real-world data distribution. By utilizing the relativity of blurriness, our approach efficiently ensures the restored brightness and structure of latent images and further generalizes deblurring performance to handle varying spatial and temporal scales of motion blur in a self-distillation manner. Our method is extensively evaluated, demonstrating remarkable performance, and we also introduce a real-world dataset consisting of multi-scale blurry frames and events to facilitate research in event-based deblurring.