In recent years, point cloud representation has become one of the research hotspots in the
field of computer vision, and has been widely used in many fields, such as autonomous …

There has been an emerging paradigm shift from the era of “internet AI” to “embodied AI,”
where AI algorithms and agents no longer learn from datasets of images, videos or text …

Natural language processing and 2D vision models have attained remarkable proficiency on
many tasks primarily by escalating the scale of training data. However, 3D vision tasks have …

The recognition capabilities of current state-of-the-art 3D models are limited by datasets with
a small number of annotated data and a pre-defined set of categories. In its 2D counterpart …

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of
large-scale real-scanned 3D databases. To facilitate the development of 3D perception …

Large-scale pre-trained models have shown promising open-world performance for both
vision and language tasks. However, their transferred capacity on 3D point clouds is still …

PointNet++ is one of the most influential neural architectures for point cloud understanding.
Although the accuracy of PointNet++ has been largely surpassed by recent networks such …

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth
of ImageNet drives a remarkable trend of" learning from large-scale data" in computer vision …

Mainstream 3D representation learning approaches are built upon contrastive or generative
modeling pretext tasks, where great improvements in performance on various downstream …

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 …