UW-ProCCaps: UnderWater Progressive Colourisation with Capsules

TL;DR

This paper introduces UW-ProCCaps, a capsule-based machine learning model that reconstructs color in underwater images from luminescence channels, significantly reducing storage needs and outperforming existing methods.

Contribution

The novel UW-ProCCaps model uses capsules and progressive adversarial training for underwater color reconstruction, a first in greyscale underwater image colorization.

Findings

Reduces storage space by 66% for underwater images.

Outperforms state-of-the-art colorization methods on four benchmarks.

Enhances image quality more effectively than current enhancement models.

Abstract

Underwater images are fundamental for studying and understanding the status of marine life. We focus on reducing the memory space required for image storage while the memory space consumption in the collecting phase limits the time lasting of this phase leading to the need for more image collection campaigns. We present a novel machine-learning model that reconstructs the colours of underwater images from their luminescence channel, thus saving 2/3 of the available storage space. Our model specialises in underwater colour reconstruction and consists of an encoder-decoder architecture. The encoder is composed of a convolutional encoder and a parallel specialised classifier trained with webly-supervised data. The encoder and the decoder use layers of capsules to capture the features of the entities in the image. The colour reconstruction process recalls the progressive and the generative adversarial training procedures. The progressive training gives the ground for a generative adversarial routine focused on the refining of colours giving the image bright and saturated colours which bring the image back to life. We validate the model both qualitatively and quantitatively on four benchmark datasets. This is the first attempt at colour reconstruction in greyscale underwater images. Extensive results on four benchmark datasets demonstrate that our solution outperforms state-of-the-art (SOTA) solutions. We also demonstrate that the generated colourisation enhances the quality of images compared to enhancement models at the SOTA.