SPLIT predicts SE(3) pose scores from local geometry in the sample frame, enabling a single diffusion model to generate grasps, handle poses, and upright placement poses for mug manipulation.
Bundlesdf: Neural 6-dof tracking and 3d reconstruction of unknown objects,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SPLIT: SE(3)-diffusion via Local Geometry-based Score Prediction for 3D Scene-to-Pose-Set Matching Problems
SPLIT predicts SE(3) pose scores from local geometry in the sample frame, enabling a single diffusion model to generate grasps, handle poses, and upright placement poses for mug manipulation.