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 2304.09121cs.CV
收藏

快速神经场景流

Fast Neural Scene Flow

The University of Adelaide(阿德莱德大学);NVIDIA(英伟达);Latitude AI

Xueqian Li, Jianqiao Zheng, Francesco Ferroni, Jhony Kaesemodel Pontes, Simon Lucey

AI总结:

本文提出快速神经场景流(FNSF),通过使用距离变换作为损失函数替代Chamfer距离,解决了神经场景流先验(NSFP)运行速度慢的问题,首次在Waymo Open和Argoverse数据集上实现无需训练的实时性能,且无分布外偏差。

摘要:

神经场景流先验(NSFP)因其对分布外(OOD)效应的固有鲁棒性以及处理密集激光雷达点云的能力,在视觉社区中引起了极大的兴趣。该方法利用坐标神经网络在运行时估计场景流,无需任何训练。然而,其速度比当前最先进的学习方法慢多达100倍。在其他应用(如图像、视频和辐射函数重建)中,加速坐标网络运行时性能的创新主要集中在架构变化上。在本文中,我们证明场景流是不同的——主要的计算瓶颈来自损失函数本身(即Chamfer距离)。此外,我们重新发现了距离变换(DT)作为一种高效、无需对应关系的损失函数,极大地加速了运行时优化。我们的快速神经场景流(FNSF)方法首次在两个最大的开放自动驾驶(AV)激光雷达数据集Waymo Open和Argoverse上报告了与学习方法相当、无需任何训练或OOD偏差的实时性能。

英文摘要:

Neural Scene Flow Prior (NSFP) is of significant interest to the vision community due to its inherent robustness to out-of-distribution (OOD) effects and its ability to deal with dense lidar points. The approach utilizes a coordinate neural network to estimate scene flow at runtime, without any training. However, it is up to 100 times slower than current state-of-the-art learning methods. In other applications such as image, video, and radiance function reconstruction innovations in speeding up the runtime performance of coordinate networks have centered upon architectural changes. In this paper, we demonstrate that scene flow is different -- with the dominant computational bottleneck stemming from the loss function itself (i.e., Chamfer distance). Further, we rediscover the distance transform (DT) as an efficient, correspondence-free loss function that dramatically speeds up the runtime optimization. Our fast neural scene flow (FNSF) approach reports for the first time real-time performance comparable to learning methods, without any training or OOD bias on two of the largest open autonomous driving (AV) lidar datasets Waymo Open and Argoverse.

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。

↑