E-CIR: Event-Enhanced Continuous Intensity Recovery

TL;DR

E-CIR is a novel method that uses event data to convert blurry images into sharp, realistic videos by modeling intensity changes over time with a deep learning approach.

Contribution

It introduces a new framework that leverages event data to enhance deblurring, including a parametric function model and a refinement module for visual consistency.

Findings

Produces smoother, more realistic deblurred videos

Outperforms state-of-the-art event-enhanced deblurring methods

Demonstrates effective use of event data for temporal intensity modeling

Abstract

A camera begins to sense light the moment we press the shutter button. During the exposure interval, relative motion between the scene and the camera causes motion blur, a common undesirable visual artifact. This paper presents E-CIR, which converts a blurry image into a sharp video represented as a parametric function from time to intensity. E-CIR leverages events as an auxiliary input. We discuss how to exploit the temporal event structure to construct the parametric bases. We demonstrate how to train a deep learning model to predict the function coefficients. To improve the appearance consistency, we further introduce a refinement module to propagate visual features among consecutive frames. Compared to state-of-the-art event-enhanced deblurring approaches, E-CIR generates smoother and more realistic results. The implementation of E-CIR is available at https://github.com/chensong1995/E-CIR.