Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors
This work addresses the challenge of partial occlusions in object pose estimation, which is critical for applications like robotics and augmented reality, representing an incremental improvement over existing methods.
The paper tackles the problem of robust rigid object pose estimation under partial occlusions by proposing a pose refinement method that learns reprojection errors via a CNN, outperforming state-of-the-art results on two out of three metrics on the Occlusion LINEMOD benchmark.
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.