BOP: Benchmark for 6D Object Pose Estimation

TL;DR

This paper introduces BOP, a comprehensive benchmark for 6D object pose estimation from RGB-D images, including diverse datasets, evaluation methodology, and analysis of recent methods to advance the field.

Contribution

It provides a unified benchmark with multiple datasets, a standardized evaluation protocol, and a comparative analysis of state-of-the-art methods for 6D pose estimation.

Findings

Point-pair feature methods outperform others

New datasets under varying lighting conditions

Evaluation system enables continuous benchmarking

Abstract

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.