TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Rong, Li, ShiJie, Chen, Xieyuanli, Ma, Teli, Gall, Juergen, Liang, Junwei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917638636044288
author Li, Rong
Li, ShiJie
Chen, Xieyuanli
Ma, Teli
Gall, Juergen
Liang, Junwei
author_facet Li, Rong
Li, ShiJie
Chen, Xieyuanli
Ma, Teli
Gall, Juergen
Liang, Junwei
contents LiDAR semantic segmentation plays a crucial role in enabling autonomous driving and robots to understand their surroundings accurately and robustly. A multitude of methods exist within this domain, including point-based, range-image-based, polar-coordinate-based, and hybrid strategies. Among these, range-image-based techniques have gained widespread adoption in practical applications due to their efficiency. However, they face a significant challenge known as the ``many-to-one'' problem caused by the range image's limited horizontal and vertical angular resolution. As a result, around 20% of the 3D points can be occluded. In this paper, we present TFNet, a range-image-based LiDAR semantic segmentation method that utilizes temporal information to address this issue. Specifically, we incorporate a temporal fusion layer to extract useful information from previous scans and integrate it with the current scan. We then design a max-voting-based post-processing technique to correct false predictions, particularly those caused by the ``many-to-one'' issue. We evaluated the approach on two benchmarks and demonstrated that the plug-in post-processing technique is generic and can be applied to various networks.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07849
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation
Li, Rong
Li, ShiJie
Chen, Xieyuanli
Ma, Teli
Gall, Juergen
Liang, Junwei
Computer Vision and Pattern Recognition
LiDAR semantic segmentation plays a crucial role in enabling autonomous driving and robots to understand their surroundings accurately and robustly. A multitude of methods exist within this domain, including point-based, range-image-based, polar-coordinate-based, and hybrid strategies. Among these, range-image-based techniques have gained widespread adoption in practical applications due to their efficiency. However, they face a significant challenge known as the ``many-to-one'' problem caused by the range image's limited horizontal and vertical angular resolution. As a result, around 20% of the 3D points can be occluded. In this paper, we present TFNet, a range-image-based LiDAR semantic segmentation method that utilizes temporal information to address this issue. Specifically, we incorporate a temporal fusion layer to extract useful information from previous scans and integrate it with the current scan. We then design a max-voting-based post-processing technique to correct false predictions, particularly those caused by the ``many-to-one'' issue. We evaluated the approach on two benchmarks and demonstrated that the plug-in post-processing technique is generic and can be applied to various networks.
title TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.07849