UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer
This work solves the problem of poor image quality in underwater photography for applications like marine research and robotics, representing an incremental advance by integrating transformers and semi-supervised learning into an existing domain.
The paper tackles underwater image enhancement by proposing UWFormer, a semi-supervised multi-scale transformer network that addresses limitations in CNNs and data scarcity, achieving state-of-the-art performance on benchmarks with improvements in both quantitative metrics and visual quality.
Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack the multi-scale enhancement, and global perception field is also limited. (ii) The scarcity of paired real-world underwater datasets poses a significant challenge, and the utilization of synthetic image pairs could lead to overfitting. To address the aforementioned problems, this paper introduces a Multi-scale Transformer-based Network called UWFormer for enhancing images at multiple frequencies via semi-supervised learning, in which we propose a Nonlinear Frequency-aware Attention mechanism and a Multi-Scale Fusion Feed-forward Network for low-frequency enhancement. Besides, we introduce a special underwater semi-supervised training strategy, where we propose a Subaqueous Perceptual Loss function to generate reliable pseudo labels. Experiments using full-reference and non-reference underwater benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of both quantity and visual quality.