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-based 3D point cloud recognition has benefited various applications. Without
specially considering the LiDAR point distribution, most current methods suffer from …

Training a 3D scene understanding model requires complicated human annotations, which
are laborious to collect and result in a model only encoding close-set object semantics. In …

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 …

With the rapid development of sensor technologies and the widespread use of laser
scanning equipment, point clouds, as the main data form and an important information …

We introduce a novel superpoint-based transformer architecture for efficient semantic
segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition …

Learning per-point semantic features from the hierarchical feature pyramid is essential for
point cloud semantic segmentation. However, most previous methods suffered from …

Abstract We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and
3D data for weakly supervised point cloud segmentation. Research studies have shown that …

Multi-modal 3D scene understanding has gained considerable attention due to its wide
applications in many areas, such as autonomous driving and human-computer interaction …

Open-vocabulary 3D instance segmentation is cutting-edge for its ability to segment 3D
instances without predefined categories. However progress in 3D lags behind its 2D …