HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds

Xiuye Gu, Yijie Wang, Chongruo Wu, Yong Jae Lee, Panqu Wang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 3254-3263

Abstract


We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds. Inspired by Bilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, and CorrBCL operations that restore structural information from unstructured point clouds, and fuse information from two consecutive point clouds. Operating on discrete and sparse permutohedral lattice points, our architectural design is parsimonious in computational cost. Our model can efficiently process a pair of point cloud frames at once with a maximum of 86K points per frame. Our approach achieves state-of-the-art performance on the FlyingThings3D and KITTI Scene Flow 2015 datasets. Moreover, trained on synthetic data, our approach shows great generalization ability on real-world data and on different point densities without fine-tuning.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Gu_2019_CVPR,
author = {Gu, Xiuye and Wang, Yijie and Wu, Chongruo and Lee, Yong Jae and Wang, Panqu},
title = {HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}