Point Cloud Segmentation Using Sparse Temporal Local Attention

12/01/2021
by   Joshua Knights, et al.
15

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally temporal in nature, there is still limited exploration of exploiting point cloud sequences for 3D seman-tic segmentation. In this paper we propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames to provide a rich temporal context to the decoder. Using the sparse local neighbourhood enables our approach to gather features more flexibly than those which directly match point features, and more efficiently than those which perform expensive global attention over the whole point cloud frame. We achieve a competitive mIoU of 64.3 significant improvement over the single-frame baseline in our ablation studies.

READ FULL TEXT
research
08/12/2020

ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation

Recent works of point clouds show that mulit-frame spatio-temporal model...
research
02/07/2022

Temporal Point Cloud Completion with Pose Disturbance

Point clouds collected by real-world sensors are always unaligned and sp...
research
11/21/2020

MoNet: Motion-based Point Cloud Prediction Network

Predicting the future can significantly improve the safety of intelligen...
research
12/20/2020

Anchor-Based Spatial-Temporal Attention Convolutional Networks for Dynamic 3D Point Cloud Sequences

Recently, learning based methods for the robot perception from the image...
research
06/01/2021

RAI-Net: Range-Adaptive LiDAR Point Cloud Frame Interpolation Network

LiDAR point cloud frame interpolation, which synthesizes the intermediat...
research
08/13/2022

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

Few-shot segmentation of point cloud remains a challenging task, as ther...
research
05/24/2017

VANETs Meet Autonomous Vehicles: A Multimodal 3D Environment Learning Approach

In this paper, we design a multimodal framework for object detection, re...

Please sign up or login with your details

Forgot password? Click here to reset