EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement

TL;DR

EvRWKV introduces a continuous cross-modal interaction framework for low-light image enhancement using event cameras, significantly improving image quality and downstream semantic segmentation performance.

Contribution

The paper presents EvRWKV, a novel dual-domain framework that effectively fuses event and image data for enhanced low-light image enhancement.

Findings

Outperforms image-only methods by 1.79 dB and 1.85 dB PSNR on SDE and SDSD datasets.

Achieves a 35.44% improvement in mIoU for semantic segmentation.

Demonstrates effective feature consistency from textures to semantics.

Abstract

Event cameras offer significant potential for Low-light Image Enhancement (LLIE), yet existing fusion approaches are constrained by a fundamental dilemma: early fusion struggles with modality heterogeneity, while late fusion severs crucial feature correlations. To address these limitations, we propose EvRWKV, a novel framework that enables continuous cross-modal interaction through dual-domain processing, which mainly includes a Cross-RWKV Module to capture fine-grained temporal and cross-modal dependencies, and an Event Image Spectral Fusion Enhancer (EISFE) module to perform joint adaptive frequency-domain denoising and spatial-domain alignment. This continuous interaction maintains feature consistency from low-level textures to high-level semantics. Extensive experiments on the real-world SDE and SDSD datasets demonstrate that EvRWKV significantly outperforms only image-based methods by 1.79 dB and 1.85 dB in PSNR, respectively. To further validate the practical utility of our method for downstream applications, we evaluated its impact on semantic segmentation. Experiments demonstrate that images enhanced by EvRWKV lead to a significant 35.44% improvement in mIoU.