Related papers: 4DPC$^2$hat: Towards Dynamic Point Cloud Understan…

The scale and quality of point cloud datasets constrain the advancement of point cloud learning. Recently, with the development of multi-modal learning, the incorporation of domain-agnostic prior knowledge from other modalities, such as…

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks. Meanwhile, in-context…

Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities. However, there are no publicly standardized benchmarks to assess the abilities of MLLMs in understanding the 4D objects (3D…

This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are…

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task…

While massively scaling both data and models have become central in NLP and 2D vision, their benefits for 3D point cloud understanding remain limited. We study the initial step of scaling 3D point cloud understanding under a realistic…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained…

Recently, the advancements in Virtual/Augmented Reality (VR/AR) have driven the demand for Dynamic Point Clouds (DPC). Unlike static point clouds, DPCs are capable of capturing temporal changes within objects or scenes, offering a more…

Recent advances in multi-modal pre-training methods have shown promising effectiveness in learning 3D representations by aligning multi-modal features between 3D shapes and their corresponding 2D counterparts. However, existing multi-modal…

Large and rich data is a prerequisite for effective training of deep neural networks. However, the irregularity of point cloud data makes manual annotation time-consuming and laborious. Self-supervised representation learning, which…

In perception, multiple sensory information is integrated to map visual information from 2D views onto 3D objects, which is beneficial for understanding in 3D environments. But in terms of a single 2D view rendered from different angles,…

We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection.…

Recent advances in Large Multimodal Models (LMM) have made it possible for various applications in human-machine interactions. However, developing LMMs that can comprehend, reason, and plan in complex and diverse 3D environments remains a…

Point cloud has drawn more and more research attention as well as real-world applications. However, many of these applications (e.g. autonomous driving and robotic manipulation) are actually based on sequential point clouds (i.e. four…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…

Multimodal Large Language Models (MLLMs) have excelled in 2D image-text comprehension and image generation, but their understanding of the 3D world is notably deficient, limiting progress in 3D language understanding and generation. To…

Recently, state space models have exhibited strong global modeling capabilities and linear computational complexity in contrast to transformers. This research focuses on applying such architecture to more efficiently and effectively model…

Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior efforts often rely on explicit 3D inputs or specialized model architectures, we ask:…

This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…