paper-with-me

홈 › Papers

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

2025-07-01 · Wenjie Cai, Qingguo Meng, Zhenyu Wang, Xingbo Dong, Zhe Jin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.03184

Code (0)

등록된 구현이 없습니다.

Tasks

Low-Light Image EnhancementSemantic Segmentation

Similar Papers 제목 키워드 기반

RWKV-UI: UI Understanding with Enhanced Perception and Reasoning

2025-02-06 · Jiaxi Yang, Haowen Hou

Existing Visual Language Modelsoften struggle with information loss and limited reasoning abilities when handling high-resolution web interfaces that combine complex visual, textual, and interactive elements. These chall…

Language ModelingLanguage Modelling

ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer

2025-01-26 · Lin Yueyu, Li Zhiyuan, Peter Yue, Liu Xiao

As is known, hybrid quadratic and subquadratic attention models in multi-head architectures have surpassed both Transformer and Linear RNN models , with these works primarily focusing on reducing KV complexity and improv…

Language ModelingLanguage ModellingTransfer Learning

Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation

2025-06-12 · Zhenhuan Zhou

Medical image segmentation is a fundamental and key technology in computer-aided diagnosis and treatment. Previous methods can be broadly classified into three categories: convolutional neural network (CNN) based, Transf…

Image SegmentationLong-range modelingMedical Image SegmentationSegmentation+1

Efficient RWKV-based Representation Learning for 3D Point Clouds

2026-06-09 · Yun Liu, Xuefeng Yan, Liangliang Nan, Xianzhi Li 외 arxiv

The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling global dependencies. However, when dire…

Representation LearningPoint Clouds

U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV

2025-07-15 · Hongbo Ye, Fenghe Tang, Peiang Zhao, Zhen Huang 외

Achieving equity in healthcare accessibility requires lightweight yet high-performance solutions for medical image segmentation, particularly in resource-limited settings. Existing methods like U-Net and its variants oft…

Computational EfficiencyImage SegmentationLong-range modelingMedical Image Segmentation+1