Related papers: PointCAT: Cross-Attention Transformer for point cl…

Transformer-based networks have achieved impressive performance in 3D point cloud understanding. However, most of them concentrate on aggregating local features, but neglect to directly model global dependencies, which results in a limited…

Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to…

We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3D features are complementary for point cloud segmentation.…

Transformer models have achieved promising performances in point cloud segmentation. However, most existing attention schemes provide the same feature learning paradigm for all points equally and overlook the enormous difference in size…

The recent surge in 3D data acquisition has spurred the development of geometric deep learning models for point cloud processing, boosted by the remarkable success of transformers in natural language processing. While point cloud…

Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking…

We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud. Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers. Specifically, we…

Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features…

Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

With the rapid progress of deep convolutional neural networks, in almost all robotic applications, the availability of 3D point clouds improves the accuracy of 3D semantic segmentation methods. Rendering of these irregular, unstructured,…

3D object detection is a crucial research topic in computer vision, which usually uses 3D point clouds as input in conventional setups. Recently, there is a trend of leveraging multiple sources of input data, such as complementing the 3D…

Point cloud segmentation, which helps us understand the environment of specific structures and objects, can be performed in class-specific and class-agnostic ways. We propose a novel region-based transformer model called Region-Transformer…

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature…

Time series forecasting is crucial for applications across multiple domains and various scenarios. Although Transformer models have dramatically advanced the landscape of forecasting, their effectiveness remains debated. Recent findings…

Medical image segmentation has made significant progress in recent years. Deep learning-based methods are recognized as data-hungry techniques, requiring large amounts of data with manual annotations. However, manual annotation is expensive…

Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbations. In this paper, we delve into boosting the general…