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

arXiv: https://arxiv.org/abs/2509.20171 · HTML: https://mlsanity.com/paper/2509.20171/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [Why do tree-based models still outperform deep learning on tabular data?](https://mlsanity.com/paper/2207.08815/) (2022)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Semantic Segmentation of Underwater Imagery: Dataset and Benchmark](https://mlsanity.com/paper/2004.01241/) (2020)
- [A Comparative Analysis of XGBoost](https://mlsanity.com/paper/1911.01914/) (2019)
- [Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset](https://mlsanity.com/paper/2406.06039/) (2024)
- [Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain](https://mlsanity.com/paper/1904.02215/) (2019)
- [Eiffel Tower: A Deep-Sea Underwater Dataset for Long-Term Visual Localization](https://mlsanity.com/paper/2305.05301/) (2023)
- [Investigation of the Challenges of Underwater-Visual-Monocular-SLAM](https://mlsanity.com/paper/2306.08738/) (2023)
- [Knowledge Distillation for Feature Extraction in Underwater VSLAM](https://mlsanity.com/paper/2303.17981/) (2023)
- [Evaluating XGBoost for Balanced and Imbalanced Data: Application to Fraud Detection](https://mlsanity.com/paper/2303.15218/) (2023)
- [Performance Evaluation of 3D Keypoint Detectors and Descriptors on Coloured Point Clouds in Subsea Environments](https://mlsanity.com/paper/2209.12881/) (2022)
- [Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images](https://mlsanity.com/paper/2504.08253/) (2025)

## Built on by (most cited first, 2 of 2)

- [UEOF: A Benchmark Dataset for Underwater Event-Based Optical Flow](https://mlsanity.com/paper/2601.10054/) (2026)
- [BALTIC: A Benchmark and Cross-Domain Strategy for 3D Reconstruction Across Air and Underwater Domains Under Varying Illumination](https://mlsanity.com/paper/2604.19133/) (2026)

## Abstract (arXiv)

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 textitOptical 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.