Multi-view object pose estimation from correspondence distributions and epipolar geometry

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

In many automation tasks involving manipulation of rigid objects, the poses of the objects must be acquired. Vision-based pose estimation using a single RGB or RGB-D sensor is especially popular due to its broad applicability. However, single-view pose estimation is inherently limited by depth ambiguity and ambiguities imposed by various phenom-ena like occlusion, self-occlusion, reflections, etc. Aggregation of information from multiple views can potentially resolve these ambiguities, but the current state-of-the-art multi-view pose estimation method only uses multiple views to aggregate single-view pose estimates, and thus rely on obtaining good single-view estimates. We present a multi-view pose estimation method which aggregates learned 2D-3D distributions from multiple views for both the initial estimate and optional refinement. Our method performs probabilistic sampling of 3D-3D correspondences under epipolar constraints using learned 2D-3D correspondence distributions which are implicitly trained to respect visual ambiguities such as symmetry. Evaluation on the T-LESS dataset shows that our method reduces pose estimation errors by 80–91% compared to the best single-view method, and we present state-of-the-art results on T-LESS with four views, even compared with methods using five and eight views.
OriginalsprogEngelsk
Titel2023 IEEE International Conference on Robotics and Automation (ICRA)
ForlagIEEE
Publikationsdato2023
Sider1786-1792
ISBN (Elektronisk)979-8-3503-2365-8
DOI
StatusUdgivet - 2023
Begivenhed2023 IEEE International Conference on Robotics and Automation (ICRA) - London, Storbritannien
Varighed: 29. maj 20232. jun. 2023

Konference

Konference2023 IEEE International Conference on Robotics and Automation (ICRA)
Land/OmrådeStorbritannien
ByLondon
Periode29/05/202302/06/2023

Fingeraftryk

Dyk ned i forskningsemnerne om 'Multi-view object pose estimation from correspondence distributions and epipolar geometry'. Sammen danner de et unikt fingeraftryk.

Citationsformater