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

2025-08-06

AI Summary

Underwater images suffer from severe color distortion, blurriness, and low contrast due to light absorption and scattering. To address these challenges, this work challenges the prevailing multi-scale feature fusion paradigm and systematically investigates the untapped potential of single-scale features in underwater image enhancement (UIE), proposing the Single-Scale Decomposition Network (SSD-Net). SSD-Net introduces an asymmetric clean/degradation layer decoupling mechanism, synergistically integrating CNN-based local modeling with Transformer-based global modeling. It incorporates a Parallel Feature Decomposition Block (PFDB) and a Bidirectional Feature Communication Block (BFCB), embedding efficient attention and adaptive sparse Transformers, alongside cross-layer residual connections. Evaluated on multiple benchmark datasets, SSD-Net achieves state-of-the-art performance—matching or surpassing leading multi-scale methods—while significantly reducing model parameters (−38%) and computational cost (FLOPs −42%).

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Enhancing underwater images degraded by light effects
• Challenging multi-scale feature reliance in reconstruction
• Exploring single-scale feature potential via decomposition network

Innovation

• Single-scale feature extraction for underwater enhancement
• Asymmetrical decomposition into clean and degradation layers
• Combines CNN and Transformer via PFDB and BFCB modules