Related papers: Attention-Guided Multi-Scale Local Reconstruction …

Following the successes in the fields of vision and language, self-supervised pretraining via masked autoencoding of 3D point set data, or Masked Point Modeling (MPM), has achieved state-of-the-art accuracy in various downstream tasks.…

Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges,…

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry information, which is also…

In recent years, point cloud analysis methods based on the Transformer architecture have made significant progress, particularly in the context of multimedia applications such as 3D modeling, virtual reality, and autonomous systems.…

We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods…

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to exploit masked autoencoding for learning 3D representations…

The manual annotation for large-scale point clouds is still tedious and unavailable for many harsh real-world tasks. Self-supervised learning, which is used on raw and unlabeled data to pre-train deep neural networks, is a promising…

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,…

Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Exploiting fine-grained semantic features on point cloud is still challenging due to its irregular and sparse structure in a non-Euclidean space. Among existing studies, PointNet provides an efficient and promising approach to learn shape…

It is challenging to reconstruct 3D point clouds in unseen classes from single 2D images. Instead of object-centered coordinate system, current methods generalized global priors learned in seen classes to reconstruct 3D shapes from unseen…

Integrating domain knowledge into deep learning has emerged as a promising direction for improving model interpretability, generalization, and data efficiency. In this work, we present a novel knowledge-guided ViT-based Masked Autoencoder…

Efficient analysis of point clouds holds paramount significance in real-world 3D applications. Currently, prevailing point-based models adhere to the PointNet++ methodology, which involves embedding and abstracting point features within a…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

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.…

Self-supervised learning has not been fully explored for point cloud analysis. Current frameworks are mainly based on point cloud reconstruction. Given only 3D coordinates, such approaches tend to learn local geometric structures and…

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories…

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…