We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image. The training data consists of a texture-mapped 3D object model or images of the object in known 6D poses. The benchmark comprises of: i) eight datasets in a unified format that cover different practical scenarios, including two new datasets focusing on varying lighting conditions, ii) an evaluation methodology with a pose-error function that deals with pose ambiguities, iii) a comprehensive evaluation of 15 diverse recent methods that captures the status quo of the field, and iv) an online evaluation system that is open for continuous submission of new results. The evaluation shows that methods based on point-pair features currently perform best, outperforming template matching methods, learning-based methods and methods based on 3D local features. The project website is available at bop.felk.cvut.cz.
@article{arxiv.1808.08319,
title = {BOP: Benchmark for 6D Object Pose Estimation},
author = {Tomas Hodan and Frank Michel and Eric Brachmann and Wadim Kehl and Anders Glent Buch and Dirk Kraft and Bertram Drost and Joel Vidal and Stephan Ihrke and Xenophon Zabulis and Caner Sahin and Fabian Manhardt and Federico Tombari and Tae-Kyun Kim and Jiri Matas and Carsten Rother},
journal= {arXiv preprint arXiv:1808.08319},
year = {2018}
}