Related papers: PointCG: Self-supervised Point Cloud Learning via …

With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on…

Completing the whole 3D structure based on an incomplete point cloud is a challenging task, particularly when the residual point cloud lacks typical structural characteristics. Recent methods based on cross-modal learning attempt to…

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 language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia.…

Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training. By contrast, unsupervised learning of point cloud data has received much less…

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing…

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser…

Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint…

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact…

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…

Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods on the synthetic…

Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach. However, it remains open whether such a framework generalizes to the unique challenges…

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…

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…

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore…

Masked autoencoder has been widely explored in point cloud self-supervised learning, whereby the point cloud is generally divided into visible and masked parts. These methods typically include an encoder accepting visible patches…

We propose Point-PNG, a novel self-supervised learning framework that generates conditional pseudo-negatives in the latent space to learn point cloud representations that are both discriminative and transformation-sensitive. Conventional…

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…