arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08945cs.CVcs.AIcs.LGcs.RO
收藏

刚性三维场景流的弱监督学习

Weakly Supervised Learning of Rigid 3D Scene Flow

Stanford University(斯坦福大学);NVIDIA(英伟达);ETH Zurich(苏黎世联邦理工学院)

Zan Gojcic, Or Litany, Andreas Wieser, Leonidas J. Guibas, Tolga Birdal

摘要:

我们提出了一个数据驱动的场景流估计算法,利用观察,许多3D场景可以解释为刚体移动代理的集合。在我们的方法的核心在于一个深的架构,能够在\textbf{object-level}的原因,考虑与其他3D任务的3D场景流。这种对象级别的抽象,使我们能够放松的要求,密集的场景流监督更简单的二进制背景分割掩模和自我运动注释。我们温和的监督要求使我们的方法非常适合最近发布的自动驾驶的大规模数据汇集,其中不包含密集的场景流注释。作为输出,我们的模型提供了低级别的线索,如逐点流和更高级别的线索,如整体场景理解在刚性对象的水平。我们进一步提出了一个测试时优化细化预测的刚性场景流。我们在四个不同的自动驾驶数据集上展示了我们方法的有效性和泛化能力。我们在\url{github.com/zgojcic/Rigid3DSceneFlow}下发布源代码和预训练模型。

英文摘要:

We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the core of our method lies a deep architecture able to reason at the \textbf{object-level} by considering 3D scene flow in conjunction with other 3D tasks. This object level abstraction, enables us to relax the requirement for dense scene flow supervision with simpler binary background segmentation mask and ego-motion annotations. Our mild supervision requirements make our method well suited for recently released massive data collections for autonomous driving, which do not contain dense scene flow annotations. As output, our model provides low-level cues like pointwise flow and higher-level cues such as holistic scene understanding at the level of rigid objects. We further propose a test-time optimization refining the predicted rigid scene flow. We showcase the effectiveness and generalization capacity of our method on four different autonomous driving datasets. We release our source code and pre-trained models under \url{github.com/zgojcic/Rigid3DSceneFlow}.

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。

↑