Related papers: DeltaConv: Anisotropic Operators for Geometric Dee…

Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several…

Deep neural networks for 3D point cloud understanding have achieved remarkable success in object classification and recognition, yet recent work shows that these models remain highly vulnerable to adversarial perturbations. Existing 3D…

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by…

The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many…

This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that…

Mechanical metamaterials enable precise control over structural properties, but their design method remains challenging due to their complex structure. Although additive manufacturing has expanded geometric freedom, navigating this vast and…

Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic…

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…

Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from…

Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a…

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional…

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D…

Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality (e.g. saddle points), due to the nature of nonconvex optimization. To address this fundamental challenge, in this…

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to…

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing…

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input…

Geometric deep learning has gained much attention in recent years due to more available data acquired from non-Euclidean domains. Some examples include point clouds for 3D models and wireless sensor networks in communications. Graphs are…

Point cloud processing has become a cornerstone technology in many 3D vision tasks. However, arbitrary rotations introduce variations in point cloud orientations, posing a long-standing challenge for effective representation learning. The…

We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…