Lasermix for semi-supervised lidar semantic segmentation

L Kong, J Ren, L Pan, Z Liu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Densely annotating LiDAR point clouds is costly, which often restrains the scalability of fully-
supervised learning methods. In this work, we study the underexplored semi-supervised …

Multi-modal data-efficient 3d scene understanding for autonomous driving

L Kong, X Xu, J Ren, W Zhang, L Pan… - … on Pattern Analysis …, 2025 - ieeexplore.ieee.org
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous
driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully …

Helimos: A dataset for moving object segmentation in 3d point clouds from heterogeneous lidar sensors

H Lim, S Jang, B Mersch, J Behley… - 2024 IEEE/RSJ …, 2024 - ieeexplore.ieee.org
Moving object segmentation (MOS) using a 3D light detection and ranging (LiDAR) sensor is
crucial for scene understanding and identification of moving objects. Despite the availability …

Fine-Tuning Point Cloud Transformers with Dynamic Aggregation

J Fei, Z Deng - … IEEE International Conference on Robotics and …, 2024 - ieeexplore.ieee.org
Point clouds play an important role in 3D analysis, which has broad applications in robotics
and autonomous driving. The pre-training fine-tuning paradigm has shown great potential in …

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds

AH Gebrehiwot, D Hurych… - 2023 IEEE/RSJ …, 2023 - ieeexplore.ieee.org
Deep perception models have to reliably cope with an open-world setting of domain shifts
induced by different geographic regions, sensor properties, mounting positions, and several …

Učení 3D Vnímání Pomocí Neanotovaných Data

P Vacek - 2024 - search.proquest.com
Integrace technologiı́ 3D počı́tačového viděnı́, zejména bodových mraků LiDARu (Light
Detection and Ranging), zásadnı́m způsobem revolucionizovala oblasti jako je autonomnı́ …

Učení 3D vnímání pomocí neanotovaných dat

V Patrik - 2024 - dspace.cvut.cz
Integrace technologiı́ 3D počı́tačového viděnı́, zejména bodových mraků LiDARu (Light
Detection and Ranging), zásadnı́m způsobem revolucionizovala oblasti jako je autonomnı́ …