Mesh-based Photorealistic and Real-time 3D Mapping for Robust Visual Perception of Autonomous Underwater Vehicle

TL;DR

This paper introduces a real-time, photorealistic 3D mapping system for autonomous underwater vehicles that combines neural network-based image enhancement with mesh-based mapping to improve underwater perception.

Contribution

It presents a novel integration of learning-based image enhancement and mesh-based mapping tailored for underwater environments, enabling lightweight and photorealistic 3D mapping.

Findings

Enhanced pose estimation and mapping quality with neural network-based image enhancement.

Achieved lightweight, real-time, photorealistic 3D mapping using mesh expansion.

Validated effectiveness through real-world and synthetic underwater datasets.

Abstract

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a learning-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. Furthermore, for sensitive tasks like inspecting cracks, photorealistic mapping is very important. However, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.