Related papers: Deformation-based In-Context Learning for Point Cl…

Existing point cloud representation learning methods primarily rely on data-driven strategies to extract geometric information from large amounts of scattered data. However, most methods focus solely on the spatial distribution features of…

Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to…

The rise of large-scale models has catalyzed in-context learning as a powerful approach for multitasking, particularly in natural language and image processing. However, its application to 3D point cloud tasks has been largely unexplored.…

In this paper, we present DV-Matcher, a novel learning-based framework for estimating dense correspondences between non-rigidly deformable point clouds. Learning directly from unstructured point clouds without meshing or manual labelling,…

Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

Research in manipulation of deformable objects is typically conducted on a limited range of scenarios, because handling each scenario on hardware takes significant effort. Realistic simulators with support for various types of deformations…

Automatic synthesis of high quality 3D shapes is an ongoing and challenging area of research. While several data-driven methods have been proposed that make use of neural networks to generate 3D shapes, none of them reach the level of…

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…

As two fundamental representation modalities of 3D objects, 3D point clouds and multi-view 2D images record shape information from different domains of geometric structures and visual appearances. In the current deep learning era,…

We present Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes. The key characteristics are the following techniques that exploit 3D positional knowledge for point cloud matching: 1) An…

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…

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, two drawbacks hinder their practical application. Firstly, the positional embedding of masked…

Masked point modeling has become a promising scheme of self-supervised pre-training for point clouds. Existing methods reconstruct either the original points or related features as the objective of pre-training. However, considering the…

For a long time, the point cloud completion task has been regarded as a pure generation task. After obtaining the global shape code through the encoder, a complete point cloud is generated using the shape priorly learnt by the networks.…

Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc.…

Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and…

Semantic scene reconstruction from point cloud is an essential and challenging task for 3D scene understanding. This task requires not only to recognize each instance in the scene, but also to recover their geometries based on the partial…

Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative semantic features from…

Most masked point cloud modeling (MPM) methods follow a regression paradigm to reconstruct the coordinate or feature of masked regions. However, they tend to over-constrain the model to learn the details of the masked region, resulting in…