Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors

TL;DR

This paper introduces a CNN-based pose refinement method that estimates reprojection errors to improve 3D object pose accuracy, especially under partial occlusions, outperforming current methods on key benchmarks.

Contribution

The proposed pose refinement approach leverages a simplified learning task to enhance robustness against occlusions, using synthetic and real data for training.

Findings

Outperforms state-of-the-art on two Occlusion LINEMOD metrics

Effective with synthetic data training

Achieves comparable results on the final metric

Abstract

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.