6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting

TL;DR

6DOPE-GS introduces a fast, online, model-free 6D object pose estimation and tracking method leveraging Gaussian Splatting, enabling real-time performance with high accuracy and dynamic scene reconstruction.

Contribution

The paper presents a novel Gaussian Splatting-based approach for efficient, real-time, model-free 6D object pose estimation and tracking from RGB-D data.

Findings

Matches state-of-the-art accuracy in pose tracking and reconstruction.

Achieves a 5× speedup over existing methods.

Demonstrates real-time tracking in dynamic, real-world scenarios.

Abstract

Efficient and accurate object pose estimation is an essential component for modern vision systems in many applications such as Augmented Reality, autonomous driving, and robotics. While research in model-based 6D object pose estimation has delivered promising results, model-free methods are hindered by the high computational load in rendering and inferring consistent poses of arbitrary objects in a live RGB-D video stream. To address this issue, we present 6DOPE-GS, a novel method for online 6D object pose estimation \& tracking with a single RGB-D camera by effectively leveraging advances in Gaussian Splatting. Thanks to the fast differentiable rendering capabilities of Gaussian Splatting, 6DOPE-GS can simultaneously optimize for 6D object poses and 3D object reconstruction. To achieve the necessary efficiency and accuracy for live tracking, our method uses incremental 2D Gaussian Splatting with an intelligent dynamic keyframe selection procedure to achieve high spatial object coverage and prevent erroneous pose updates. We also propose an opacity statistic-based pruning mechanism for adaptive Gaussian density control, to ensure training stability and efficiency. We evaluate our method on the HO3D and YCBInEOAT datasets and show that 6DOPE-GS matches the performance of state-of-the-art baselines for model-free simultaneous 6D pose tracking and reconstruction while providing a 5$\times$ speedup. We also demonstrate the method's suitability for live, dynamic object tracking and reconstruction in a real-world setting.