WaterFormer: Global-Local Transformer for Underwater Image Enhancement with Environment Adaptor

Underwater image enhancement (UIE) is crucial for high-level vision in underwater robotics. While convolutional neural networks (CNNs) have made significant achievements in UIE, the locality of convolution poses a challenge in capturing the global context. In contrast, Transformer-based networks, adept at handling long-range dependencies, have shown promise in various vision tasks. Nonetheless, directly applying Transformer to UIE faces critical challenges: 1) it tends to produce results with coarse details due to the negligence of local texture; 2) the varicolored degraded images require the network to be adaptable to different underwater environments. In this paper, we propose a novel Transformer-based network that can effectively leverage both the global contextual and local detailed information with some key designs (global-local Transformer block and detail-enhanced skip connector) while being computationally efficient. Moreover, by introducing a simple but effective learnable environment adaptor, the pro- posed network is flexible to deal with different underwater environments. Extensive experiments have been conducted and demonstrated the superiority of our proposed network com- pared with other state-of-the-art methods both qualitatively and quantitatively. The code will be publicly available at https://github.com/RockWenJJ/WaterFormer.