Multi-Bracket High Dynamic Range Imaging with Event Cameras

TL;DR

This paper introduces a novel multi-bracket HDR imaging pipeline that combines standard cameras with event cameras, improving robustness and image quality in dynamic scenes by leveraging high temporal resolution and dynamic range of events.

Contribution

It presents the first multi-bracket HDR method integrating event cameras with standard cameras, along with a new dataset for evaluation.

Findings

PSNR improved by up to 5dB on synthetic data

PSNR improved by up to 0.7dB on real-world data

Enhanced robustness in dynamic scenes

Abstract

Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low dynamic range (LDR) images captured at different exposure times. While these methods work well in static scenes, dynamic scenes remain a challenge since the LDR images still suffer from saturation and noise. In such scenarios, event cameras would be a valid complement, thanks to their higher temporal resolution and dynamic range. In this paper, we propose the first multi-bracket HDR pipeline combining a standard camera with an event camera. Our results show better overall robustness when using events, with improvements in PSNR by up to 5dB on synthetic data and up to 0.7dB on real-world data. We also introduce a new dataset containing bracketed LDR images with aligned events and HDR ground truth.