Contrastive learning has emerged as a promising paradigm for 3D open-world
understanding, jointly with text, image, and point cloud. In this paper, we introduce …

Contrastive learning has emerged as a promising paradigm for 3D open-world
understanding ie aligning point cloud representation to image and text embedding space …

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

Large foundation models have recently emerged as a prominent focus of interest, attaining
superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts …

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via
leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on …

State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale
datasets and well-defined category sets. Recent advances in multi-modal pre-training have …

The success of deep learning heavily relies on large-scale data with comprehensive labels,
which is more expensive and time-consuming to fetch in 3D compared to 2D images or …

3D Shape represented as point cloud has achieve advancements in multimodal pre-training
to align image and language descriptions, which is curial to object identification …

The rising importance of 3D representation learning, pivotal in computer vision, autonomous
driving, and robotics, is evident. However, a prevailing trend, which straightforwardly …

Pre-training by numerous image data has become de-facto for robust 2D representations. In
contrast, due to the expensive data processing, a paucity of 3D datasets severely hinders …