Optical Ocean Recipes: Creating Realistic Datasets to Facilitate Underwater Vision Research

2025-09-24

AI Summary

Underwater machine vision evaluation is hindered by the difficulty of reproducing and controlling real marine optical conditions—such as spectral attenuation, scattering-induced blur, and color distortion—while existing datasets lack generalizability across water types and imaging conditions. Method: We propose the first reproducible experimental framework based on an “optical ocean recipe”: calibrated chromatic and scattering additives in controlled tanks precisely emulate diverse seawater optical properties; combined with a physics-based imaging model, it generates multi-task datasets with pixel-accurate ground truth for water parameter estimation, image restoration, segmentation, visual SLAM, and synthesis. Contribution/Results: This framework enables the first quantitative control and reproducible emulation of water optical properties, establishing a benchmark environment that balances realism and controllability. Experiments validate its effectiveness on image restoration and visual SLAM. Code and datasets will be open-sourced to advance standardized evaluation of underwater vision algorithms.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

The development and evaluation of machine vision in underwater environments remains challenging, often relying on trial-and-error-based testing tailored to specific applications. This is partly due to the lack of controlled, ground-truthed testing environments that account for the optical challenges, such as color distortion from spectrally variant light attenuation, reduced contrast and blur from backscatter and volume scattering, and dynamic light patterns from natural or artificial illumination. Additionally, the appearance of ocean water in images varies significantly across regions, depths, and seasons. However, most machine vision evaluations are conducted under specific optical water types and imaging conditions, therefore often lack generalizability. Exhaustive testing across diverse open-water scenarios is technically impractical. To address this, we introduce the extit{Optical Ocean Recipes}, a framework for creating realistic datasets under controlled underwater conditions. Unlike synthetic or open-water data, these recipes, using calibrated color and scattering additives, enable repeatable and controlled testing of the impact of water composition on image appearance. Hence, this provides a unique framework for analyzing machine vision in realistic, yet controlled underwater scenarios. The controlled environment enables the creation of ground-truth data for a range of vision tasks, including water parameter estimation, image restoration, segmentation, visual SLAM, and underwater image synthesis. We provide a demonstration dataset generated using the Optical Ocean Recipes and briefly demonstrate the use of our system for two underwater vision tasks. The dataset and evaluation code will be made available.

Problem

• Addressing lack of controlled testing environments for underwater machine vision
• Overcoming optical challenges like color distortion and backscatter in water
• Providing generalizable datasets across diverse underwater imaging conditions

Innovation

• Framework creates realistic controlled underwater datasets
• Uses calibrated color and scattering additives
• Enables repeatable testing of water composition effects