UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization

TL;DR

This paper introduces UWCVGAN, a novel underwater image enhancement model using capsule vector quantization, which improves image quality and detail while enabling image compression for efficient storage.

Contribution

The paper proposes UWCVGAN, a new underwater image enhancement model that leverages capsule layer-based feature quantization for improved quality and compression capabilities.

Findings

Achieves high-quality underwater image enhancement with fine details.

Reduces image storage space by a factor of 3 using the encoder.

Outperforms state-of-the-art methods on benchmark datasets.

Abstract

The degradation in the underwater images is due to wavelength-dependent light attenuation, scattering, and to the diversity of the water types in which they are captured. Deep neural networks take a step in this field, providing autonomous models able to achieve the enhancement of underwater images. We introduce Underwater Capsules Vectors GAN UWCVGAN based on the discrete features quantization paradigm from VQGAN for this task. The proposed UWCVGAN combines an encoding network, which compresses the image into its latent representation, with a decoding network, able to reconstruct the enhancement of the image from the only latent representation. In contrast with VQGAN, UWCVGAN achieves feature quantization by exploiting the clusterization ability of capsule layer, making the model completely trainable and easier to manage. The model obtains enhanced underwater images with high quality and fine details. Moreover, the trained encoder is independent of the decoder giving the possibility to be embedded onto the collector as compressing algorithm to reduce the memory space required for the images, of factor $3\times$. \myUWCVGAN{ }is validated with quantitative and qualitative analysis on benchmark datasets, and we present metrics results compared with the state of the art.