相关论文: Toward Availability Attacks in 3D Point Clouds

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…

Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized…

Convolutional Neural Networks (CNNs) have emerged as a powerful strategy for most object detection tasks on 2D images. However, their power has not been fully realised for detecting 3D objects in point clouds directly without converting…

Visual localization is the problem of estimating the camera pose of a given image with respect to a known scene. Visual localization algorithms are a fundamental building block in advanced computer vision applications, including Mixed and…

Unsupervised domain adaptation (UDA) frameworks have shown good generalization capabilities for 3D point cloud semantic segmentation models on clean data. However, existing works overlook adversarial robustness when the source domain itself…

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These…

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space;…

The Chamfer Distance (CD) is a cornerstone objective function for point cloud completion, yet its inherent symmetric weighting mechanism limits the quality of the generated results. By penalizing local detail deviations and global coverage…

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the…

With the increasing attention in various 3D safety-critical applications, point cloud learning models have been shown to be vulnerable to adversarial attacks. Although existing 3D attack methods achieve high success rates, they delve into…

3D vision with real-time LiDAR-based point cloud data became a vital part of autonomous system research, especially perception and prediction modules use for object classification, segmentation, and detection. Despite their success, point…

Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used…

Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise heterogeneity, leading to perceptible perturbations. We propose…

The widespread deployment of Deep Neural Networks (DNNs) for 3D point cloud processing starkly contrasts with their susceptibility to security breaches, notably backdoor attacks. These attacks hijack DNNs during training, embedding triggers…

Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in the resolution of the 3D point clouds. To solve this issue, previous studies use 3D registration techniques. Out of these proposed techniques,…

Point cloud registration is a central theme in computer vision, with alignment algorithms continuously improving for greater robustness. Commonly used methods evaluate Euclidean distances between point clouds and minimize an objective…

Recent attacks on federated learning (FL) can introduce malicious model updates that circumvent widely adopted Euclidean distance-based detection methods. This paper proposes a novel defense strategy, referred to as LayerCAM-AE, designed to…

Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this…

Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars. However, the point clouds captured by the 3D range sensor are commonly sparse and unstructured, challenging…

Point clouds are often sparse and incomplete. Existing shape completion methods are incapable of generating details of objects or learning the complex point distributions. To this end, we propose a cascaded refinement network together with…