BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects

TL;DR

The BOP Challenge 2023 evaluates state-of-the-art 6D object pose estimation methods for both seen and unseen objects, introducing new tasks and demonstrating significant progress in accuracy and runtime efficiency since 2017.

Contribution

This paper presents the BOP Challenge 2023, including new tasks for unseen objects, evaluation datasets, and benchmark results, advancing the field of model-based 6D object pose estimation.

Findings

GenFlow achieved comparable accuracy to 2020 methods for unseen objects

GPose improved runtime by 43% over 2022 methods for seen objects

Overall 6D localization accuracy for seen objects increased by over 50% since 2017

Abstract

We present the evaluation methodology, datasets and results of the BOP Challenge 2023, the fifth in a series of public competitions organized to capture the state of the art in model-based 6D object pose estimation from an RGB/RGB-D image and related tasks. Besides the three tasks from 2022 (model-based 2D detection, 2D segmentation, and 6D localization of objects seen during training), the 2023 challenge introduced new variants of these tasks focused on objects unseen during training. In the new tasks, methods were required to learn new objects during a short onboarding stage (max 5 minutes, 1 GPU) from provided 3D object models. The best 2023 method for 6D localization of unseen objects (GenFlow) notably reached the accuracy of the best 2020 method for seen objects (CosyPose), although being noticeably slower. The best 2023 method for seen objects (GPose) achieved a moderate accuracy improvement but a significant 43% run-time improvement compared to the best 2022 counterpart (GDRNPP). Since 2017, the accuracy of 6D localization of seen objects has improved by more than 50% (from 56.9 to 85.6 AR_C). The online evaluation system stays open and is available at: http://bop.felk.cvut.cz/.