Related papers: SOE-Net: A Self-Attention and Orientation Encoding…

Human pose estimation (HPE) is one of the most challenging tasks in computer vision as humans are deformable by nature and thus their pose has so much variance. HPE aims to correctly identify the main joint locations of a single person or…

Place recognition is one of the hot research fields in automation technology and is still an open issue, Camera and Lidar are two mainstream sensors used in this task, Camera-based methods are easily affected by illumination and season…

Self-attention-based networks have achieved remarkable performance in sequential recommendation tasks. A crucial component of these models is positional encoding. In this study, we delve into the learned positional embedding, demonstrating…

Learning new representations of 3D point clouds is an active research area in 3D vision, as the order-invariant point cloud structure still presents challenges to the design of neural network architectures. Recent works explored learning…

Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting…

Environment perception including detection, classification, tracking, and motion prediction are key enablers for automated driving systems and intelligent transportation applications. Fueled by the advances in sensing technologies and…

Most of the existing deep learning based methods for vessel segmentation neglect two important aspects of retinal vessels, one is the orientation information of vessels, and the other is the contextual information of the whole fundus…

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such…

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…

Recent advancements in machine learning, particularly through deep learning architectures like PointNet, have transformed the processing of three-dimensional (3D) point clouds, significantly improving 3D object classification and…

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 this paper, we propose Attention Based Decomposition Network (ABD-Net), for point cloud decomposition into basic geometric shapes namely, plane, sphere, cone and cylinder. We show improved performance of 3D object classification using…

Post-disaster damage assessment requires rapid and accurate semantic segmentation of 3D point clouds to identify critical infrastructure such as damaged buildings and roads. Early Point Transformers (e.g., PTv1, PTv2) relied on…

Recognizing human actions from point cloud sequence has attracted tremendous attention from both academia and industry due to its wide applications. However, most previous studies on point cloud action recognition typically require complex…

Accurate localization on autonomous driving cars is essential for autonomy and driving safety, especially for complex urban streets and search-and-rescue subterranean environments where high-accurate GPS is not available. However current…

Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained…

We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms. Our SA-Net exploits the rich…

Point cloud segmentation is one of the most important tasks in computer vision with widespread scientific, industrial, and commercial applications. The research thereof has resulted in many breakthroughs in 3D object and scene…

How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting…

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…