UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization

by   Rita Pucci, et al.

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×. is validated with quantitative and qualitative analysis on benchmark datasets, and we present metrics results compared with the state of the art.


page 2

page 5

page 15

page 17

page 18

page 19

page 20


PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators

Due to the light absorption and scattering induced by the water medium, ...

UW-ProCCaps: UnderWater Progressive Colourisation with Capsules

Underwater images are fundamental for studying and understanding the sta...

All-In-One Underwater Image Enhancement using Domain-Adversarial Learning

Raw underwater images are degraded due to wavelength dependent light att...

Underwater Image Enhancement via Learning Water Type Desensitized Representations

For underwater applications, the effects of light absorption and scatter...

Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding

Underwater images suffer from color casts and low contrast due to wavele...

L^2UWE: A Framework for the Efficient Enhancement of Low-Light Underwater Images Using Local Contrast and Multi-Scale Fusion

Images captured underwater often suffer from suboptimal illumination set...

On the limits of perceptual quality measures for enhanced underwater images

The appearance of objects in underwater images is degraded by the select...

Please sign up or login with your details

Forgot password? Click here to reset