arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.01253cs.CV
收藏

神经场景流先验

Neural Scene Flow Prior

Argo AI;The University of Adelaide(阿德莱德大学)

Xueqian Li, Jhony Kaesemodel Pontes, Simon Lucey

摘要:

在深度学习革命之前,许多感知算法都是基于运行时优化以及强先验/正则化惩罚。在计算机视觉中,这方面的一个主要例子是光学和场景流。监督学习在很大程度上取代了显式正则化的需求。相反,它们依赖于大量的标记数据来捕获先验统计数据,而这些数据并不总是容易用于许多问题。虽然采用优化来学习神经网络,但该网络的权重在运行时被冻结。因此,这些学习解决方案是特定于领域的,并且不能很好地推广到其他统计上不同的场景。本文回顾了场景流问题,主要依赖于运行时优化和强正则化。这里的一个核心创新是包含一个神经场景流先验,它使用神经网络的架构作为一种新型的隐式正则化。与基于学习的场景流方法不同,优化发生在运行时,我们的方法不需要离线数据集,这使得它非常适合在自动驾驶等新环境中部署。我们表明,完全基于多层感知器(MLP)的架构可以用作场景流之前。我们的方法达到竞争力-如果不是更好-场景流基准的结果。此外,我们的神经先验的隐式和连续场景流表示允许我们估计点云序列中的密集长期对应关系。密集的运动信息由场景流场表示,其中点可以通过整合运动矢量而在时间上传播。我们证明了这样的能力,积累了激光雷达点云序列。

英文摘要:

Before the deep learning revolution, many perception algorithms were based on runtime optimization in conjunction with a strong prior/regularization penalty. A prime example of this in computer vision is optical and scene flow. Supervised learning has largely displaced the need for explicit regularization. Instead, they rely on large amounts of labeled data to capture prior statistics, which are not always readily available for many problems. Although optimization is employed to learn the neural network, the weights of this network are frozen at runtime. As a result, these learning solutions are domain-specific and do not generalize well to other statistically different scenarios. This paper revisits the scene flow problem that relies predominantly on runtime optimization and strong regularization. A central innovation here is the inclusion of a neural scene flow prior, which uses the architecture of neural networks as a new type of implicit regularizer. Unlike learning-based scene flow methods, optimization occurs at runtime, and our approach needs no offline datasets -- making it ideal for deployment in new environments such as autonomous driving. We show that an architecture based exclusively on multilayer perceptrons (MLPs) can be used as a scene flow prior. Our method attains competitive -- if not better -- results on scene flow benchmarks. Also, our neural prior's implicit and continuous scene flow representation allows us to estimate dense long-term correspondences across a sequence of point clouds. The dense motion information is represented by scene flow fields where points can be propagated through time by integrating motion vectors. We demonstrate such a capability by accumulating a sequence of lidar point clouds.

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。

↑