Aquaformer: Underwater Image Enhancement via Adaptive Transformer

Document Type

Conference Article

Publication Title

Proceedings of the International Joint Conference on Neural Networks

Abstract

Water causes degradation of quality in optical images captured underwater due to its physical properties of absorption and scattering. This degradation is further aggravated by the increase in water depth and the presence of contaminated water. Transformers in the vision domain have made a quantum leap in many vision tasks such as detection, and segmentation but yet to make any progress in enhancing degraded underwater images. We propose a transformer-based model named 'Aquaformer' which makes four major contributions: an adaptive layer normalization, replacement of masked cyclic shift with symmetric padding in window partitioning, a novel aggregation mechanism, and an adjustable fusion approach. These succeed in making the model a very powerful one, producing significantly better performance compared to the latest state-of-the-art methods. Testing on multiple benchmark datasets, employing both quantitative and qualitative metrics, establishes its supremacy.

DOI

10.1109/IJCNN60899.2024.10650431

Publication Date

1-1-2024

Link to Full Text

Share

COinS