Less: Label-efficient semantic segmentation for lidar point clouds

M Liu, Y Zhou, CR Qi, B Gong, H Su… - European conference on …, 2022 - Springer
Semantic segmentation of LiDAR point clouds is an important task in autonomous driving.
However, training deep models via conventional supervised methods requires large …

Slim: Self-supervised lidar scene flow and motion segmentation

SA Baur, DJ Emmerichs, F Moosmann… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recently, several frameworks for self-supervised learning of 3D scene flow on point clouds
have emerged. Scene flow inherently separates every scene into multiple moving agents …

A systematic literature review on long‐term localization and mapping for mobile robots

RB Sousa, HM Sobreira, AP Moreira - Journal of Field Robotics, 2023 - Wiley Online Library
Long‐term operation of robots creates new challenges to Simultaneous Localization and
Mapping (SLAM) algorithms. Long‐term SLAM algorithms should adapt to recent changes …

Ogc: Unsupervised 3d object segmentation from rigid dynamics of point clouds

Z Song, B Yang - Advances in Neural Information …, 2022 - proceedings.neurips.cc
In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike
all existing methods which usually require a large amount of human annotations for full …

Receding moving object segmentation in 3d lidar data using sparse 4d convolutions

B Mersch, X Chen, I Vizzo, L Nunes… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
A key challenge for autonomous vehicles is to navigate in unseen dynamic environments.
Separating moving objects from static ones is essential for navigation, pose estimation, and …

Hierarchical point-based active learning for semi-supervised point cloud semantic segmentation

Z Xu, B Yuan, S Zhao, Q Zhang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Impressive performance on point cloud semantic segmentation has been achieved by fully-
supervised methods with large amounts of labelled data. As it is labour-intensive to acquire …

Improving nighttime driving-scene segmentation via dual image-adaptive learnable filters

W Liu, W Li, J Zhu, M Cui, X Xie… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Semantic segmentation on driving-scene images is vital for autonomous driving. Although
encouraging performance has been achieved on daytime images, the performance on …

Banana: Banach fixed-point network for pointcloud segmentation with inter-part equivariance

C Deng, J Lei, WB Shen… - Advances in Neural …, 2024 - proceedings.neurips.cc
Equivariance has gained strong interest as a desirable network property that inherently
ensures robust generalization. However, when dealing with complex systems such as …

Human body shape completion with implicit shape and flow learning

B Zhou, D Meng, JS Franco… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In this paper, we investigate how to complete human body shape models by combining
shape and flow estimation given two consecutive depth images. Shape completion is a …

Adv3d: Generating safety-critical 3d objects through closed-loop simulation

J Sarva, J Wang, J Tu, Y Xiong, S Manivasagam… - arXiv preprint arXiv …, 2023 - arxiv.org
Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to
ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate …