Spectroformer: Multi-Domain Query Cascaded Transformer Network For Underwater Image Enhancement

Underwater images often suffer from color distortion, haze, and limited visibility due to light refraction and absorption in water. These challenges significantly impact autonomous underwater vehicle applications, necessitating efficient image enhancement techniques. To address these challenges, we propose a Multi-Domain Query Cascaded Transformer Network for underwater image enhancement. Our approach includes a novel Multi-Domain Query Cascaded Attention mechanism that integrates localized transmission features and global illumination features. To improve feature propagation from the encoder to the decoder, we propose a Spatio-Spectro Fusion-Based Attention Block. Additionally, we introduce a Hybrid Fourier-Spatial Up-sampling Block, which uniquely combines Fourier and spatial upsampling techniques to enhance feature resolution effectively. We evaluate our method on benchmark synthetic and real-world underwater image datasets, demonstrating its superiority through extensive ablation studies and comparative analysis. The testing code is available at: https://github.com/Mdraqibkhan/Spectroformer.

1. Introduction

Underwater Image Enhancement (UIE) algorithms are vital for aquatic exploration with wide applications in Autonomous Underwater Vehicles (AUVs), underwater mine detection [52], submerged robots [17], and among other fields. However, the major challenges in underwater imaging include poor equipment quality [27], insufficient illumination, and light absorption/scattering [45]. These issues lead to quality problems like color shifts, haziness, and blurriness, reducing image interoperability and thus limiting its application in the underwater world [32].