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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Wenjie, Meng, Qingguo, Wang, Zhenyu, Dong, Xingbo, Jin, Zhe
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911260342222848
author Cai, Wenjie
Meng, Qingguo
Wang, Zhenyu
Dong, Xingbo
Jin, Zhe
author_facet Cai, Wenjie
Meng, Qingguo
Wang, Zhenyu
Dong, Xingbo
Jin, Zhe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03184
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement
Cai, Wenjie
Meng, Qingguo
Wang, Zhenyu
Dong, Xingbo
Jin, Zhe
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.03184