URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration

TL;DR

The paper introduces URWKV, a novel low-light image restoration model that utilizes multi-state analysis and adaptive mechanisms to effectively handle complex degradations with fewer resources.

Contribution

It proposes the URWKV model with multi-state perspective, including novel modules like LAN and SSF, for flexible and efficient low-light image restoration.

Findings

Outperforms state-of-the-art models on benchmark datasets.

Requires fewer parameters and less computation.

Effectively handles complex degradations with adaptive modules.

Abstract

Existing low-light image enhancement (LLIE) and joint LLIE and deblurring (LLIE-deblur) models have made strides in addressing predefined degradations, yet they are often constrained by dynamically coupled degradations. To address these challenges, we introduce a Unified Receptance Weighted Key Value (URWKV) model with multi-state perspective, enabling flexible and effective degradation restoration for low-light images. Specifically, we customize the core URWKV block to perceive and analyze complex degradations by leveraging multiple intra- and inter-stage states. First, inspired by the pupil mechanism in the human visual system, we propose Luminance-adaptive Normalization (LAN) that adjusts normalization parameters based on rich inter-stage states, allowing for adaptive, scene-aware luminance modulation. Second, we aggregate multiple intra-stage states through exponential moving average approach, effectively capturing subtle variations while mitigating information loss inherent in the single-state mechanism. To reduce the degradation effects commonly associated with conventional skip connections, we propose the State-aware Selective Fusion (SSF) module, which dynamically aligns and integrates multi-state features across encoder stages, selectively fusing contextual information. In comparison to state-of-the-art models, our URWKV model achieves superior performance on various benchmarks, while requiring significantly fewer parameters and computational resources.