RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds

04/01/2022
by   Ramy Battrawy, et al.
0

The proposed RMS-FlowNet is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation which can operate on point clouds of high density. For hierarchical scene flow estimation, the existing methods depend on either expensive Farthest-Point-Sampling (FPS) or structure-based scaling which decrease their ability to handle a large number of points. Unlike these methods, we base our fully supervised architecture on Random-Sampling (RS) for multiscale scene flow prediction. To this end, we propose a novel flow embedding design which can predict more robust scene flow in conjunction with RS. Exhibiting high accuracy, our RMS-FlowNet provides a faster prediction than state-of-the-art methods and works efficiently on consecutive dense point clouds of more than 250K points at once. Our comprehensive experiments verify the accuracy of RMS-FlowNet on the established FlyingThings3D data set with different point cloud densities and validate our design choices. Additionally, we show that our model presents a competitive ability to generalize towards the real-world scenes of KITTI data set without fine-tuning.

READ FULL TEXT

page 3

page 5

research
06/12/2019

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

We present a novel deep neural network architecture for end-to-end scene...
research
05/04/2023

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

3D scene flow estimation aims to estimate point-wise motions between two...
research
08/08/2023

DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

Point clouds are naturally sparse, while image pixels are dense. The inc...
research
11/27/2019

PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds

We propose a novel end-to-end deep scene flow model, called PointPWC-Net...
research
05/27/2023

GMSF: Global Matching Scene Flow

We tackle the task of scene flow estimation from point clouds. Given a s...
research
04/01/2021

FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds

Scene flow depicts the dynamics of a 3D scene, which is critical for var...
research
04/18/2023

Fast Neural Scene Flow

Scene flow is an important problem as it provides low-level motion cues ...

Please sign up or login with your details

Forgot password? Click here to reset