Towards Scaling Marine Perception with Synthetic Data

2026-09-17

AI Summary

本文针对水下环境缺乏标记数据的问题，提出了一种基于OceanSim的合成数据生成管道，用于训练水下感知模型。

Abstract

Scalable machine learning in challenging underwater environments is strongly limited by the lack of labeled real-world training data. This data is often expensive and laborious to gather, making large-scale real-world data challenging to gather and curate. However, simulated data can help close the gap, enabling many learning-based tasks for underwater perception. In this work, we extend OceanSim, an IsaacSim-based underwater perception simulator, with a Synthetic Data Generation (SDG) pipeline for training models to be used in underwater scenarios. The proposed pipeline enables users to generate large, automatically labeled, photorealistic datasets with configurable scene appearance, structure, and sensor settings. We evaluate the pipeline on a real-world sea urchin detection task and study how different forms of synthetic scene variation affect sim-to-real performance. Based on these experiments, we discuss findings on our results, main limitations of the current pipeline and identify future directions for improving underwater rendering fidelity, scene diversity, and the evaluation of sim-to-real generalization. The open-source code can be found at https://github.com/umfieldrobotics/OceanSim.

Problem

• Scalable machine learning
• underwater environments
• labeled real-world training data
• simulated data
• underwater perception

Innovation

• Synthetic Data Generation
• Underwater Perception
• Simulation
• Photorealistic Datasets
• Sim-to-Real Performance