Denoising Diffusion as a New Framework for Underwater Images
Nilesh Jain, Elie Alhajjar
TL;DR
The paper addresses the challenge of degraded underwater imagery and limited dataset diversity by proposing a diffusion-based framework that combines Stable Diffusion v2.0 with ControlNet to perform image enhancement, inpainting, and data augmentation. This multi-component pipeline targets noise, color distortion, and lighting artifacts while enabling restoration of occluded regions and generation of diverse training samples. The approach emphasizes expanding datasets to include stereo, wide-angle, macro, and close-up imagery, thereby improving generalization for marine ecosystem analysis and related applications. If effective, the framework could significantly improve underwater image quality and enable more robust downstream analyses in marine archaeology, biodiversity monitoring, and resource assessment.
Abstract
Underwater images play a crucial role in ocean research and marine environmental monitoring since they provide quality information about the ecosystem. However, the complex and remote nature of the environment results in poor image quality with issues such as low visibility, blurry textures, color distortion, and noise. In recent years, research in image enhancement has proven to be effective but also presents its own limitations, like poor generalization and heavy reliance on clean datasets. One of the challenges herein is the lack of diversity and the low quality of images included in these datasets. Also, most existing datasets consist only of monocular images, a fact that limits the representation of different lighting conditions and angles. In this paper, we propose a new plan of action to overcome these limitations. On one hand, we call for expanding the datasets using a denoising diffusion model to include a variety of image types such as stereo, wide-angled, macro, and close-up images. On the other hand, we recommend enhancing the images using Controlnet to evaluate and increase the quality of the corresponding datasets, and hence improve the study of the marine ecosystem. Tags - Underwater Images, Denoising Diffusion, Marine ecosystem, Controlnet