Exploring Fourier Prior and Event Collaboration for Low-Light Image Enhancement

TL;DR

This paper introduces a novel two-stage low-light image enhancement method leveraging event camera data, employing Fourier analysis and dynamic fusion to improve image quality under challenging lighting conditions.

Contribution

The work proposes a decoupled enhancement pipeline with Fourier-based visibility restoration and a dynamic fusion strategy, exploiting modality-specific advantages for superior low-light image enhancement.

Findings

Outperforms state-of-the-art models in low-light enhancement tasks

Effective use of Fourier space for visibility restoration

Dynamic alignment improves structure refinement

Abstract

The event camera, benefiting from its high dynamic range and low latency, provides performance gain for low-light image enhancement. Unlike frame-based cameras, it records intensity changes with extremely high temporal resolution, capturing sufficient structure information. Currently, existing event-based methods feed a frame and events directly into a single model without fully exploiting modality-specific advantages, which limits their performance. Therefore, by analyzing the role of each sensing modality, the enhancement pipeline is decoupled into two stages: visibility restoration and structure refinement. In the first stage, we design a visibility restoration network with amplitude-phase entanglement by rethinking the relationship between amplitude and phase components in Fourier space. In the second stage, a fusion strategy with dynamic alignment is proposed to mitigate the spatial mismatch caused by the temporal resolution discrepancy between two sensing modalities, aiming to refine the structure information of the image enhanced by the visibility restoration network. In addition, we utilize spatial-frequency interpolation to simulate negative samples with diverse illumination, noise and artifact degradations, thereby developing a contrastive loss that encourages the model to learn discriminative representations. Experiments demonstrate that the proposed method outperforms state-of-the-art models.