arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.07378cs.CVcs.GRcs.LGcs.RO
收藏

BOP 2020年6D物体定位挑战赛

BOP Challenge 2020 on 6D Object Localization

Czech Technical University in Prague(布拉格捷克理工大学);German Aerospace Center(德国航空航天中心);MVTec(MVTec公司);INRIA Paris(法国国家信息与自动化研究所巴黎);Heidelberg University(海德堡大学);Technical University Dresden(德累斯顿工业大学)

Tomas Hodan, Martin Sundermeyer, Bertram Drost, Yann Labbe, Eric Brachmann, Frank Michel, Carsten Rother, Jiri Matas

摘要:

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物体姿态估计领域的现状。在2020年,为了减少合成训练和真实测试RGB图像之间的域差距,参与者获得了由BlenderProc 4 BOP生成的350 K照片级真实感训练图像,BlenderProc 4 BOP是一种新的开源和轻量级的基于物理的渲染器(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,后者在之前的挑战中占据主导地位。尽管表现最好的方法依赖于RGB-D图像通道,但在26种评估方法中,当在训练和测试超时时仅使用RGB通道时,获得了很好的结果,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最高性能CosyPose方法的关键组成部分,尽管增强,PBR图像的照片真实感被证明是有效的。在线评价系统保持开放,可在项目网站上查阅:bop.felk.cvut.cz。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑