arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08683cs.CV
收藏

用于自动驾驶的自监督支柱运动学习

Self-Supervised Pillar Motion Learning for Autonomous Driving

QCraft;Johns Hopkins University(约翰霍普金斯大学)

Chenxu Luo, Xiaodong Yang, Alan Yuille

摘要:

在高度动态的环境中与不同的交通参与者进行交互时,自动驾驶可以从运动行为理解中受益。最近,直接从点云估计类不可知运动的兴趣越来越大。当前的运动估计方法通常需要来自自动驾驶场景的大量带注释的训练数据。然而,手动标记点云是出了名的困难,容易出错和耗时。在本文中,我们试图回答的研究问题,丰富的未标记的数据汇集是否可以用于准确和有效的运动学习。为此,我们提出了一个学习框架,该框架利用来自点云和配对相机图像的自由监督信号,纯粹通过自我监督来估计运动。我们的模型包括一个基于点云的结构一致性增强概率运动掩蔽以及跨传感器运动正则化,以实现所需的自我监督。实验表明,我们的方法表现出竞争力的监督方法,并达到了国家的最先进的结果时,结合我们的自监督模型与监督微调。

英文摘要:

Autonomous driving can benefit from motion behavior comprehension when interacting with diverse traffic participants in highly dynamic environments. Recently, there has been a growing interest in estimating class-agnostic motion directly from point clouds. Current motion estimation methods usually require vast amount of annotated training data from self-driving scenes. However, manually labeling point clouds is notoriously difficult, error-prone and time-consuming. In this paper, we seek to answer the research question of whether the abundant unlabeled data collections can be utilized for accurate and efficient motion learning. To this end, we propose a learning framework that leverages free supervisory signals from point clouds and paired camera images to estimate motion purely via self-supervision. Our model involves a point cloud based structural consistency augmented with probabilistic motion masking as well as a cross-sensor motion regularization to realize the desired self-supervision. Experiments reveal that our approach performs competitively to supervised methods, and achieves the state-of-the-art result when combining our self-supervised model with supervised fine-tuning.

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。

↑