MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility

Ahsan Baidar Bakht, Zikai Jia, Muhayy Ud Din, Waseem Akram, Lyes Saad Saoud, Lakmal D. Seneviratne, Defu Lin, Shaoming He, Irfan Hussain

Abstract: Highlights•Underwater image enhancement using generative adversarial networks.•A novel GAN architecture by adding spatio-channel attention mechanism.•An extensive comparison with SOTA methods on public and private datasets