Despite the significant recent progress made on 3D point cloud semantic segmentation, the
current methods require training data for all classes at once, and are not suitable for real-life …

Existing fully-supervised point cloud segmentation methods suffer in the dynamic testing
environment with emerging new classes. Few-shot point cloud segmentation algorithms …

During the last few years, continual learning (CL) strategies for image classification and
segmentation have been widely investigated designing innovative solutions to tackle …

In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …

In this work, we address 3D novel class discovery (NCD) that discovers novel classes from
an unlabeled dataset by leveraging the knowledge of disjoint known classes. The key …

Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-
trained on a large point-cloud dataset will encounter unseen classes of 3D objects after …

In this work, we address 3D open-set recognition (OSR) that can recognize known classes
as well as be aware of unknown classes during testing. The key challenge of 3D OSR is that …

Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting
issue when a model is incrementally trained on limited data. While the Contrastive Vision …

Point clouds offer comprehensive and precise data regarding the contour and configuration
of objects. Employing such geometric and topological 3D information of objects in class …