DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting
By: Holly Dinkel , Marcel Büsching , Alberta Longhini and more
Potential Business Impact:
Helps robots tie knots by seeing and feeling.
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.
Similar Papers
SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting
CV and Pattern Recognition
Lets cameras know exactly where things are.
Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping
Robotics
Lets robots see and map places faster.
Globally Consistent RGB-D SLAM with 2D Gaussian Splatting
Robotics
Builds better 3D maps from camera pictures.