Point cloud learning has lately attracted increasing attention due to its wide applications in
many areas, such as computer vision, autonomous driving, and robotics. As a dominating …

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 …

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebImageText, and
LAION have propelled recent dramatic progress in AI. Large neural models trained on such …

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 …

We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects.
This approach utilizes pretrained models from image captioning, image-text alignment, and …

We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework,
for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to …

Interactive 3D simulations have enabled break-throughs in robotics and computer vision, but
simulating the broad diversity of environments needed for deep learning requires large …

Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation
followed by grou**. The hard predictions are made when performing semantic …

We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike
most existing models that learn to deterministically translate a latent vector to a shape, our …

We present the first systematic study on concealed object detection (COD), which aims to
identify objects that are visually embedded in their background. The high intrinsic similarities …