UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancement

TL;DR

UIESNN introduces a scale-aware spiking neural network for underwater image enhancement, leveraging multi-scale pooling and attention mechanisms to improve color fidelity and spatial coherence efficiently.

Contribution

The paper proposes a novel scale-aware SNN framework with a multi-scale pooling block and spike-driven architecture for underwater image enhancement.

Findings

UIESNN achieves state-of-the-art results on EUVP and LSUI benchmarks.

It improves color fidelity and spatial coherence over existing SNN methods.

The approach maintains competitive energy efficiency.

Abstract

Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degradations are large-scale and low-frequency, such as wavelength-dependent colour casts and scattering-induced veiling. Existing SNN restoration designs rely on locally bounded spiking perception, which can limit global correction and lead to saturated or inconsistent representations. To address these challenges, we propose a scale-aware SNN framework for UIE named UIESNN. At its core is a Multi-scale Pooling LIF Block (MPLB) that injects hierarchical multi-scale pooling responses into membrane dynamics, thereby enlarging the effective receptive field while preserving fine-grained details and inducing heterogeneous scale-dependent activations. Building on MPLB, we design a spiking residual architecture that integrates frequency decomposition and attention-based refinement in a fully spike-driven pipeline. Extensive experiments on the EUVP and LSUI benchmarks demonstrate that UIESNN achieves state-of-the-art performance among SNN-based methods, delivering improved colour fidelity and spatial coherence with competitive energy cost.