Log In Sign Up

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

by   Xingyu Liu, et al.

Understanding dynamic 3D environment is crucial for robotic agents and many other applications. We propose a novel neural network architecture called MeteorNet for learning representations for dynamic 3D point cloud sequences. Different from previous work that adopts a grid-based representation and applies 3D or 4D convolutions, our network directly processes point clouds. We propose two ways to construct spatiotemporal neighborhoods for each point in the point cloud sequence. Information from these neighborhoods is aggregated to learn features per point. We benchmark our network on a variety of 3D recognition tasks including action recognition, semantic segmentation and scene flow estimation. MeteorNet shows stronger performance than previous grid-based methods while achieving state-of-the-art performance on Synthia. MeteorNet also outperforms previous baseline methods that are able to process at most two consecutive point clouds. To the best of our knowledge, this is the first work on deep learning for dynamic raw point cloud sequences.


page 6

page 8

page 13

page 14

page 15


Sequential Point Clouds: A Survey

Point cloud has drawn more and more research attention as well as real-w...

Self-Supervised Learning of Part Mobility from Point Cloud Sequence

Part mobility analysis is a significant aspect required to achieve a fun...

Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data

In this paper, we demonstrate an end-to-end spatiotemporal gesture learn...

CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting

This paper introduces CloudLSTM, a new branch of recurrent neural networ...

Bridging the Gap: Point Clouds for Merging Neurons in Connectomics

In the field of Connectomics, a primary problem is that of 3D neuron seg...

Explaining Hierarchical Features in Dynamic Point Cloud Processing

This paper aims at bringing some light and understanding to the field of...

PointResNet: Residual Network for 3D Point Cloud Segmentation and Classification

Point cloud segmentation and classification are some of the primary task...

Code Repositories


MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences (ICCV 2019 Oral)

view repo