This paper addresses the task of estimating the 6D pose of a known 3D object from a single RGB-D image. Most modern approaches solve this task in three steps: i) Compute local features; ii) Generate a pool of pose-hypotheses; iii) Select and refine a pose from the pool. This work focuses on the second step. While all existing approaches generate the hypotheses pool via local reasoning, e.g. RANSAC or Hough-voting, we are the first to show that global reasoning is beneficial at this stage. In particular, we formulate a novel fully-connected Conditional Random Field (CRF) that outputs a very small number of pose-hypotheses. Despite the potential functions of the CRF being non-Gaussian, we give a new and efficient two-step optimization procedure, with some guarantees for optimality. We utilize our global hypotheses generation procedure to produce results that exceed state-of-the-art for the challenging "Occluded Object Dataset".
@article{arxiv.1612.02287,
title = {Global Hypothesis Generation for 6D Object Pose Estimation},
author = {Frank Michel and Alexander Kirillov and Eric Brachmann and Alexander Krull and Stefan Gumhold and Bogdan Savchynskyy and Carsten Rother},
journal= {arXiv preprint arXiv:1612.02287},
year = {2017}
}