4D Forecasting: Sequential Forecasting of 100,000 Points
Workshop Paper, ECCV '20 Workshops, August, 2020
Abstract
Predicting the future is a crucial first step to effective control. In this work, we study the problem of future prediction of 3D scenes, represented by point clouds captured by a LiDAR sensor, i.e., directly forecasting the evolution of >100,000 points that comprise a complete scene. We term this Sequential Pointcloud Forecasting (SPF). By directly predicting the densest-possible 3D representation of the future, the output contains richer information than output of prior forecasting tasks such as future object trajectories. We design a method, SPFNet, evaluate it on the KITTI and nuScenes datasets, and find that it demonstrates excellent performance on the SPF task. Our project website is at http://www.xinshuoweng.com/projects/SPF2.
BibTeX
@workshop{Weng-2020-124273,author = {Xinshuo Weng and Jianren Wang and Sergey Levine and Kris Kitani and Nicholas Rhinehart},
title = {4D Forecasting: Sequential Forecasting of 100,000 Points},
booktitle = {Proceedings of ECCV '20 Workshops},
year = {2020},
month = {August},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.