Related papers: 3DVerifier: Efficient Robustness Verification for …

The use of deep 3D point cloud models in safety-critical applications, such as autonomous driving, dictates the need to certify the robustness of these models to real-world transformations. This is technically challenging, as it requires a…

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…

3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these models against real-world deformations must be addressed…

Point clouds are extensively employed in a variety of real-world applications such as robotics, autonomous driving and augmented reality. Despite the recent success of point cloud neural networks, especially for safety-critical tasks, it is…

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…

Point cloud classification is an essential component in many security-critical applications such as autonomous driving and augmented reality. However, point cloud classifiers are vulnerable to adversarially perturbed point clouds. Existing…

The 3D deep learning community has seen significant strides in pointcloud processing over the last few years. However, the datasets on which deep models have been trained have largely remained the same. Most datasets comprise clean,…

Point clouds are widely used representations of 3D data, but determining the visibility of points from a given viewpoint remains a challenging problem due to their sparse nature and lack of explicit connectivity. Traditional methods, such…

3D point cloud classification has many safety-critical applications such as autonomous driving and robotic grasping. However, several studies showed that it is vulnerable to adversarial attacks. In particular, an attacker can make a…

The main challenge in 3D object detection from LiDAR point clouds is achieving real-time performance without affecting the reliability of the network. In other words, the detecting network must be confident enough about its predictions. In…

Diffusion models are rapidly redefining 3D anomaly detection in point cloud data. As 3D sensing becomes integral to modern manufacturing, reliable anomaly detection is essential for high-throughput quality assurance and process control. Yet…

3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in…

Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challenging conditions, under which noise or perturbations are…

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their…

Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and generalizability to…

In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represented by a 3D point…

In this work, we propose a novel two-stage framework for the efficient 3D point cloud object detection. Instead of transforming point clouds into 2D bird eye view projections, we parse the raw point cloud data directly in the 3D space yet…

In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to…

Although neural networks are widely used, it remains challenging to formally verify the safety and robustness of neural networks in real-world applications. Existing methods are designed to verify the network before deployment, which are…

We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size, resolution-invariant latent representation. This enables efficient training with…