Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
Paper i proceeding, 2020

In recent years, considerable progress has been made for the task of rigid object pose estimation from a single RGB-image, but achieving robustness to partial occlusions remains a challenging problem. Pose refinement via rendering has shown promise in order to achieve improved results, in particular, when data is scarce. In this paper we focus our attention on pose refinement, and show how to push the state-of-the-art further in the case of partial occlusions. The proposed pose refinement method leverages on a simplified learning task, where a CNN is trained to estimate the reprojection error between an observed and a rendered image. We experiment by training on purely synthetic data as well as a mixture of synthetic and real data. Current state-of-the-art results are outperformed for two out of three metrics on the Occlusion LINEMOD benchmark, while performing on-par for the final metric.

Rigid Object Pose Estimation


Partial Occlusion

Pose Refinement


Fredrik Kahl

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Digitala bildsystem och bildanalys

Proceedings of the British Machine Vision Conference 2020

31st British Machine Vision Conference, BMVC 2020
, United Kingdom,

Deep learning för 3D-igenkänning

Wallenberg AI, Autonomous Systems and Software Program, 2018-01-01 -- .


Informations- och kommunikationsteknik


Datorseende och robotik (autonoma system)

Relaterade dataset

Occlusion LINEMOD [dataset]

DOI: 10.1007/978-3-319-10605-2_35

Mer information