Litcius/Paper detail

3D SceneFlowNet: Self-Supervised 3D Scene Flow Estimation Based on Graph CNN

Yawen Lu, Yuhao Zhu, Guoyu Lu

202118 citationsDOI

Abstract

Despite deep learning approaches have achieved promising successes in 2D optical flow estimation, it is a challenge to accurately estimate scene flow in 3D space as point clouds are inherently lacking topological information. In this paper, we aim at handling the problem of self-supervised 3D scene flow estimation based on dynamic graph convolutional neural networks (GCNNs), namely 3D SceneFlowNet. To better learn geometric relationships among points, we introduce EdgeConv to learn multiple-level features in a pyramid from point clouds and a self-attention mechanism to apply the multi-level features to predict the final scene flow. Our trained model can efficiently process a pair of adjacent point clouds as input and predict a 3D scene flow accurately without any supervision. The proposed approach achieves superior performance on both synthetic ModelNet40 dataset and real LiDAR scans from KITTI Scene Flow 2015 datasets.

Topics & Concepts

Point cloudComputer scienceArtificial intelligenceConvolutional neural networkOptical flowGraphComputer visionFlow (mathematics)Pyramid (geometry)Process (computing)Point (geometry)Pattern recognition (psychology)Machine learningImage (mathematics)Theoretical computer scienceMathematicsOperating systemGeometryAdvanced Vision and ImagingOptical measurement and interference techniquesRobotics and Sensor-Based Localization