Abstract
Capturing high-quality visual content under low-light conditions remains a challenging problem due to severe noise, motion blur, and underexposure, which degrade the performance of downstream applications. Traditional frame-based low-light enhancement methods often amplify noise or fail to preserve structural details, especially in real-world scenarios. Event cameras, offering high dynamic range and microsecond temporal resolution by asynchronously capturing brightness changes, emerge as promising alternatives for low-light imaging. However, existing event-image fusion methods suffer from simplistic fusion strategies and inadequate handling of spatial-temporal misalignment and noise. To address these challenges, we propose EvRWKV, a novel framework that enables continuous cross-modal interaction through dual-domain processing. Our approach incorporates a Cross-RWKV module, leveraging the Receptance Weighted Key Value (RWKV) architecture for fine-grained temporal and cross-modal fusion, and an Event Image Spectral Fusion Enhancer (EISFE) module, which jointly performs adaptive frequency-domain noise suppression and spatial-domain deformable convolution alignment. Extensive qualitative and quantitative evaluations on real-world low-light datasets(SDE, SDSD, RELED) demonstrate that EvRWKV achieves state-of-the-art performance, effectively enhancing image quality by suppressing noise, restoring structural details, and improving visual clarity in challenging low-light conditions.
Abstract (translated)
在低光条件下捕捉高质量的视觉内容仍然是一项具有挑战性的任务，因为严重的噪声、运动模糊和曝光不足会降低下游应用的表现。传统的帧基础低光增强方法往往会放大噪声或无法保留结构细节，特别是在真实世界的场景中。事件相机通过异步捕获亮度变化提供高动态范围和微秒级的时间分辨率，成为低光成像的有前景的选择之一。然而，现有的事件图像融合方法面临着简单的融合策略以及对时空错位和噪声处理不足的问题。为了应对这些挑战，我们提出了EvRWKV，这是一个新的框架，通过双域处理实现持续跨模态交互。 我们的方法包括一个Cross-RWKV模块，利用接收权重值（Receptance Weighted Key Value, RWKV）架构进行细粒度的时间融合和跨模态融合，以及一个事件图像频谱融合增强器(EISFE)模块，该模块同时执行自适应频率域噪声抑制和空间域可变形卷积对齐。在真实世界的低光数据集（SDE、SDSD、RELED）上进行广泛的定性和定量评估表明，EvRWKV达到了最先进的性能，通过抑制噪声、恢复结构细节以及改善视觉清晰度，在具有挑战性的低光条件下有效提高了图像质量。
URL
https://arxiv.org/abs/2507.03184
