3D object detection from images, one of the fundamental and challenging problems in
autonomous driving, has received increasing attention from both industry and academia in …

The Metaverse, distinguished by its capacity to integrate the physical and digital realms
seamlessly, presents a dynamic virtual environment offering diverse opportunities for …

Unlike previous studies on the Metaverse based on Second Life, the current Metaverse is
based on the social value of Generation Z that online and offline selves are not different …

Semantic segmentation of LiDAR point clouds is an important task in autonomous driving.
However, training deep models via conventional supervised methods requires large …

Advanced 3D object detection methods usually rely on large-scale, elaborately labeled
datasets to achieve good performance. However, labeling the bounding boxes for the 3D …

We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing
methods which primarily rely on a large amount of human annotations for training neural …

To address the huge labeling cost in large-scale point cloud semantic segmentation, we
propose a novel hybrid contrastive regularization (HybridCR) framework in weakly …

Labelling point clouds fully is highly time-consuming and costly. As larger point cloud
datasets with billions of points become more common, we ask whether the full annotation is …

We study the task of weakly-supervised point cloud semantic segmentation with sparse
annotations (eg, less than 0.1% points are labeled), aiming to reduce the expensive cost of …

Current 3D segmentation methods heavily rely on large-scale point-cloud datasets, which
are notoriously laborious to annotate. Few attempts have been made to circumvent the need …