SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulation

Abstract-- Object pose estimation is a fundamental problem in robotics and computer vision, yet it remains challenging due to partial observability, occlusions, and object symmetries, which inevitably lead to pose ambiguity and multiple hypotheses consistent with the same observation. While deterministic deep networks achieve impressive performance under well-constrained conditions, they are often overconfident and fail to capture the multi-modality of the underlying pose distribution. T o address these challenges, we propose a novel probabilistic framework that leverages flow matching on the SE(3) manifold for estimating 6D object pose distributions. Unlike existing methods that regress a single deterministic output, our approach models the full pose distribution with a sample-based estimate and enables reasoning about uncertainty in ambiguous cases such as symmetric objects or severe occlusions. We achieve state-of-the-art results on Real275, YCB-V and LM-O, and demonstrate how our sample-based pose estimates can be leveraged in downstream robotic manipulation tasks such as active perception for disambiguating uncertain viewpoints, or guiding grasp synthesis in an uncertainty-aware manner . Estimating the 6D pose of objects is a fundamental problem in robotics, as it enables embodied agents to perceive, manipulate, and interact safely with their environment. In practical applications such as robotic grasping, assembly, and human-robot collaboration, it is not sufficient to output a single deterministic pose estimate. Instead, reasoning about uncertainty is critical for ensuring safe and reliable manipulation [1], [2].