Hierarchical Attention Learning of Scene Flow in 3D Point Clouds

Abstract

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous driving and service robot. This paper studies the problem of scene flow estimation from two consecutive 3D point clouds. In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer. The proposed network has a new more-for-less hierarchical architecture. The more-for-less means that the number of input points is greater than the number of output points for scene flow estimation, which brings more input information and balances the precision and resource consumption. In this hierarchical architecture, scene flow of different levels is generated and supervised respectively. A novel attentive embedding module is introduced to aggregate the features of adjacent points using a double attention method in a patch-to-patch manner. The proper layers for flow embedding and flow supervision are carefully considered in our network designment. Experiments show that the proposed network outperforms the state-of-the-art performance of 3D scene flow estimation on the FlyingThings3D and KITTI Scene Flow 2015 datasets. We also apply the proposed network to realistic LiDAR odometry task, which is an key problem in autonomous driving. The experiment results demonstrate that our proposed network can outperform the ICP-based method and shows the good practical application ability.

arXiv comment13 pages, 7 figures, under review

References in corpus (9)

• ShapeNet: An Information-Rich 3D Model Repository
• A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• MeshCNN: A Network with an Edge
• Deep Parametric Continuous Convolutional Neural Networks
• PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
• DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
• Motion-based Object Segmentation based on Dense RGB-D Scene Flow
• Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Cited by in corpus (5)

• Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences
• Unsupervised Learning of 3D Scene Flow from Monocular Camera
• Attention Models for Point Clouds in Deep Learning: A Survey
• PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization
• RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds