Abstract 3D point-clouds and 2D images are different visual representations of the physical
world. While human vision can understand both representations, computer vision models …

We present Point-BERT, a novel paradigm for learning Transformers to generalize the
concept of BERT onto 3D point cloud. Following BERT, we devise a Masked Point Modeling …

We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by
using a joint prediction from a conventional 3D model and a well-pretrained 2D model …

Abstract 3D point-cloud recognition with PointNet and its variants has received remarkable
progress. A missing ingredient, however, is the ability to automatically evaluate point-wise …

In this work, we address the challenging task of few-shot and zero-shot 3D point cloud
semantic segmentation. The success of few-shot semantic segmentation in 2D computer …

Classification and segmentation of 3D point clouds are important tasks in computer vision.
Because of the irregular nature of point clouds, most of the existing methods convert point …

The increased availability of massive point clouds coupled with their utility in a wide variety
of applications such as robotics, shape synthesis, and self-driving cars has attracted …

Pre-training across 3D vision and language remains under development because of limited
training data. Recent works attempt to transfer vision-language (VL) pre-training methods to …

As a promising scheme of self-supervised learning, masked autoencoding has significantly
advanced natural language processing and computer vision. Inspired by this, we propose a …

Although recent point cloud analysis achieves impressive progress, the paradigm of
representation learning from single modality gradually meets its bottleneck. In this work, we …