@inproceedings {pub6146,
	title = {6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting},
	author = {Yufeng Jin AND Vignesh Prasad AND Mathias Franzius AND Georgia Chalvatzaki},
	year = {2025},
	month = {October},
	abstract = {Efficient and accurate object pose estimation is an es-
sential component for modern vision systems in many ap-
plications such as Augmented Reality, autonomous driving,
and robotics. While research in model-based 6D object pose
estimation has delivered promising results, model-free meth-
ods are hindered by the high computational load in ren-
dering 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 and 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 opti-
mize for 6D object poses and 3D object reconstruction. To
achieve the necessary efficiency and accuracy for live track-
ing, 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{\texttimes} speedup. We also
demonstrate the method{\textquoteright}s suitability for live, dynamic object
tracking and reconstruction in a real-world setting.},
	publisher = {IEEE},
	booktitle = {International Conference on Computer Vision (ICCV)}
}