NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding

TL;DR

NAUTILUS is a large multimodal model designed for comprehensive underwater scene understanding, leveraging a new dataset and a feature enhancement module to improve robustness and performance in underwater exploration tasks.

Contribution

The paper introduces NautData, a large-scale underwater dataset, and a novel VFE module, advancing multi-task underwater scene understanding with improved robustness and accuracy.

Findings

VFE module enhances model performance across tasks

NAUTILUS outperforms baselines on underwater datasets

Constructed the first large-scale multi-task underwater dataset

Abstract

Underwater exploration offers critical insights into our planet and attracts increasing attention for its broader applications in resource exploration, national security, etc. We study the underwater scene understanding methods, which aim to achieve automated underwater exploration. The underwater scene understanding task demands multi-task perceptions from multiple granularities. However, the absence of large-scale underwater multi-task instruction-tuning datasets hinders the progress of this research. To bridge this gap, we construct NautData, a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks. It enables the development and thorough evaluation of the underwater scene understanding models. Underwater image degradation is a widely recognized challenge that interferes with underwater tasks. To improve the robustness of underwater scene understanding, we introduce physical priors derived from underwater imaging models and propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information. We integrate this module into renowned baselines LLaVA-1.5 and Qwen2.5-VL and build our underwater LMM, NAUTILUS. Experiments conducted on the NautData and public underwater datasets demonstrate the effectiveness of the VFE module, consistently improving the performance of both baselines on the majority of supported tasks, thus ensuring the superiority of NAUTILUS in the underwater scene understanding area. Data and models are available at https://github.com/H-EmbodVis/NAUTILUS.