Point clouds are increasingly being used to improve productivity, quality, and safety
throughout the life cycle of construction and infrastructure projects. While applicable for …

Point cloud is a widely used 3D data form, which can be produced by depth sensors, such
as Light Detection and Ranging (LIDAR) and RGB-D cameras. Being unordered and …

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 …

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 …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training
(CLIP) have shown inspirational performance on 2D visual recognition, which learns to …

Abstract Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled
text-image pairs, has demonstrated great performance in open-world vision understanding …

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 …

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 …

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts
gradually, where only a few examples per concept are available to the learner. Due to the …