This work presents DLO-Splatting, an algorithm for estimating the 3D shape of Deformable Linear Objects (DLOs) from multi-view RGB images and gripper state information through prediction-update filtering. The DLO-Splatting algorithm uses a position-based dynamics model with shape smoothness and rigidity dampening corrections to predict the object shape. Optimization with a 3D Gaussian Splatting-based rendering loss iteratively renders and refines the prediction to align it with the visual observations in the update step. Initial experiments demonstrate promising results in a knot tying scenario, which is challenging for existing vision-only methods.
@article{arxiv.2505.08644,
title = {DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting},
author = {Holly Dinkel and Marcel Büsching and Alberta Longhini and Brian Coltin and Trey Smith and Danica Kragic and Mårten Björkman and Timothy Bretl},
journal= {arXiv preprint arXiv:2505.08644},
year = {2025}
}
Comments
5 pages, 2 figures, presented at the 2025 5th Workshop: Reflections on Representations and Manipulating Deformable Objects at the IEEE International Conference on Robotics and Automation. RMDO workshop (https://deformable-workshop.github.io/icra2025/). Video (https://www.youtube.com/watch?v=CG4WDWumGXA). Poster (https://hollydinkel.github.io/assets/pdf/ICRA2025RMDO_poster.pdf)