Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
Paper in 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.

Partial Occlusion


Rigid Object Pose Estimation

Pose Refinement


Lucas Brynte

Computer vision and medical image analysis

Fredrik Kahl

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

31st British Machine Vision Conference, BMVC 2020

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

Deep Learning for 3D Recognition

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

Areas of Advance

Information and Communication Technology

Subject Categories

Computer Vision and Robotics (Autonomous Systems)

Related datasets

Occlusion LINEMOD [dataset]

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

More information

Latest update