Fabian Duffhauss, Sebastian Koch, Hanna Ziesche, Ngo Anh Vien, and Gerhard Neumann

Detecting objects and estimating their 6D poses
is essential for automated systems to interact safely with the
environment. Most 6D pose estimators, however, rely on a single
camera frame and suffer from occlusions and ambiguities due
to object symmetries. We overcome this issue by presenting
a novel symmetry-aware multi-view 6D pose estimator called
SyMFM6D. Our approach effi ciently fuses the RGB-D frames from
multiple perspectives in a deep multi-directional fusion network
and predicts predefi ned keypoints for all objects in the scene
simultaneously. Based on the keypoints and an instance semantic
segmentation, we effi ciently compute the 6D poses by least-squares
fi tting. To address the ambiguity issues for symmetric objects, we
propose a novel training procedure for symmetry-aware keypoint
detection including a new objective function. Our SyMFM6D
network signifi cantly outperforms the state-of-the-art in both
single-view and multi-view 6D pose estimation. We furthermore
show the effectiveness of our symmetry-aware training procedure
and demonstrate that our approach is robust towards inaccurate
camera calibration and dynamic camera setups.

Paper: https://arxiv.org/abs/2307.00306

Code: https://github.com/boschresearch/SyMFM6D