From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing

TL;DR

This paper introduces a novel event-guided diffusion framework that leverages high dynamic range event camera data to significantly improve dehazing performance, especially in challenging hazy conditions.

Contribution

It is the first to utilize event cameras for dehazing and proposes a diffusion model that effectively transfers HDR cues from events to enhance image clarity.

Findings

Achieves state-of-the-art dehazing results on benchmarks.

Demonstrates effectiveness of event-guided diffusion in real-world hazy scenes.

Outperforms prior methods in visual realism and structural preservation.

Abstract

Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic range. Therefore, dehazing remains ill-posed and can erase structure and illumination details. To address this, we use event cameras for dehazing for the \textbf{first time}. Event cameras offer much higher HDR ($120 dBvs.60 dB$) and microsecond latency, therefore they suit hazy scenes. In practice, transferring HDR cues from events to frames is hard because real paired data are scarce. To tackle this, we propose an event-guided diffusion model that utilizes the strong generative priors of diffusion models to reconstruct clear images from hazy inputs by effectively transferring HDR information from events. Specifically, we design an event-guided module that maps sparse HDR event features, \textit{e.g.,} edges, corners, into the diffusion latent space. This clear conditioning provides precise structural guidance during generation, improves visual realism, and reduces semantic drift. For real-world evaluation, we collect a drone dataset in heavy haze (AQI = 341) with synchronized RGB and event sensors. Experiments on two benchmarks and our dataset achieve state-of-the-art results.