Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement

TL;DR

This paper introduces SSD-Net, a novel single-scale feature decomposition network for underwater image enhancement, demonstrating that single-scale features can outperform multi-scale methods in quality and complexity.

Contribution

The paper proposes SSD-Net with an asymmetrical decomposition mechanism and dual modules, showing single-scale features are sufficient for effective underwater image enhancement.

Findings

Single-scale features can match or surpass multi-scale methods in underwater image quality.

SSD-Net reduces complexity compared to multi-scale approaches.

The architecture effectively disentangles scene-intrinsic and degradation information.

Abstract

Underwater image enhancement (UIE) techniques aim to improve visual quality of images captured in aquatic environments by addressing degradation issues caused by light absorption and scattering effects, including color distortion, blurring, and low contrast. Current mainstream solutions predominantly employ multi-scale feature extraction (MSFE) mechanisms to enhance reconstruction quality through multi-resolution feature fusion. However, our extensive experiments demonstrate that high-quality image reconstruction does not necessarily rely on multi-scale feature fusion. Contrary to popular belief, our experiments show that single-scale feature extraction alone can match or surpass the performance of multi-scale methods, significantly reducing complexity. To comprehensively explore single-scale feature potential in underwater enhancement, we propose an innovative Single-Scale Decomposition Network (SSD-Net). This architecture introduces an asymmetrical decomposition mechanism that disentangles input image into clean layer along with degradation layer. The former contains scene-intrinsic information and the latter encodes medium-induced interference. It uniquely combines CNN's local feature extraction capabilities with Transformer's global modeling strengths through two core modules: 1) Parallel Feature Decomposition Block (PFDB), implementing dual-branch feature space decoupling via efficient attention operations and adaptive sparse transformer; 2) Bidirectional Feature Communication Block (BFCB), enabling cross-layer residual interactions for complementary feature mining and fusion. This synergistic design preserves feature decomposition independence while establishing dynamic cross-layer information pathways, effectively enhancing degradation decoupling capacity.