Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point-
or voxel-based methods as they often yield better performance than the traditional range …

The robustness of 3D perception systems under natural corruptions from environments and
sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets …

Point cloud segmentation is fundamental in understanding 3D environments. However,
current 3D point cloud segmentation methods usually perform poorly on scene boundaries …

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 …

Recent advances in 3D semantic segmentation with deep neural networks have shown
remarkable success, with rapid performance increase on available datasets. However …

Modern 3D semantic instance segmentation approaches predominantly rely on specialized
voting mechanisms followed by carefully designed geometric clustering techniques. Building …

LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously,
capture precise geometry of the surrounding environment and are crucial to many …

Deep learning (DL) has become one of the mainstream and effective methods for point
cloud analysis tasks such as detection, segmentation and classification. To reduce …

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous
driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully …