This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB-D image. In 2020, to reduce the domain gap between synthetic training and real test RGB images, the participants were provided 350K photorealistic training images generated by BlenderProc4BOP, a new open-source and light-weight physically-based renderer (PBR) and procedural data generator. Methods based on deep neural networks have finally caught up with methods based on point pair features, which were dominating previous editions of the challenge. Although the top-performing methods rely on RGB-D image channels, strong results were achieved when only RGB channels were used at both training and test time - out of the 26 evaluated methods, the third method was trained on RGB channels of PBR and real images, while the fifth on RGB channels of PBR images only. Strong data augmentation was identified as a key component of the top-performing CosyPose method, and the photorealism of PBR images was demonstrated effective despite the augmentation. The online evaluation system stays open and is available on the project website: bop.felk.cvut.cz.

中文翻译：

---

2020 年 BOP 挑战赛 6D 对象定位

本文介绍了 BOP Challenge 2020 的评估方法、数据集和结果，这是一系列公开竞赛中的第三场，旨在从 RGB-D 图像中捕捉 6D 对象姿态估计领域的现状。2020 年，为了缩小合成训练和真实测试 RGB 图像之间的域差距，向参与者提供了 350K 逼真的训练图像，这些图像由 BlenderProc4BOP 生成，BlenderProc4BOP 是一种新的开源轻量级基于物理的渲染器 (PBR) 和程序数据生成器。基于深度神经网络的方法终于赶上了基于点对特征的方法，这些方法在以前的挑战中占据主导地位。尽管性能最好的方法依赖于 RGB-D 图像通道，在训练和测试时仅使用 RGB 通道时取得了很好的结果——在 26 种评估方法中，第三种方法在 PBR 和真实图像的 RGB 通道上训练，而第五种方法仅在 PBR 图像的 RGB 通道上训练。强大的数据增强被确定为表现最佳的 CosyPose 方法的关键组成部分，尽管增强，PBR 图像的照片写实效果仍被证明是有效的。在线评估系统保持开放，可在项目网站：bop.felk.cvut.cz 上获取。尽管进行了增强，但 PBR 图像的真实感仍被证明是有效的。在线评估系统保持开放，可在项目网站：bop.felk.cvut.cz 上获取。尽管进行了增强，但 PBR 图像的真实感仍被证明是有效的。在线评估系统保持开放，可在项目网站：bop.felk.cvut.cz 上获取。