Model-Based Underwater 6D Pose Estimation from RGB

TL;DR

This paper presents a novel RGB-based 6D pose estimation method for underwater objects, leveraging 2D detection to achieve higher accuracy in challenging underwater conditions, validated on synthetic and real datasets.

Contribution

The work introduces a new RGB-based 6D pose estimation pipeline specifically designed for underwater environments, with an open-source dataset and improved accuracy over existing methods.

Findings

8% more accurate pose estimates compared to similar methods

Validated on 33,920 synthetic and 10 real underwater scenes

Demonstrated real-world robotic manipulation in underwater tasks

Abstract

Object pose estimation underwater allows an autonomous system to perform tracking and intervention tasks. Nonetheless, underwater target pose estimation is remarkably challenging due to, among many factors, limited visibility, light scattering, cluttered environments, and constantly varying water conditions. An approach is to employ sonar or laser sensing to acquire 3D data, however, the data is not clear and the sensors expensive. For this reason, the community has focused on extracting pose estimates from RGB input. In this work, we propose an approach that leverages 2D object detection to reliably compute 6D pose estimates in different underwater scenarios. We test our proposal with 4 objects with symmetrical shapes and poor texture spanning across 33,920 synthetic and 10 real scenes. All objects and scenes are made available in an open-source dataset that includes annotations for object detection and pose estimation. When benchmarking against similar end-to-end methodologies for 6D object pose estimation, our pipeline provides estimates that are 8% more accurate. We also demonstrate the real world usability of our pose estimation pipeline on an underwater robotic manipulator in a reaching task.