Related papers: VA-GCN: A Vector Attention Graph Convolution Netwo…

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification…

Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional…

Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). An essential part of the ViG framework is the node-neighbor…

The analysis of 3D point clouds has diverse applications in robotics, vision and graphics. Processing them presents specific challenges since they are naturally sparse, can vary in spatial resolution and are typically unordered. Graph-based…

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic…

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a $K$-nearest neighbor (KNN) search and a…

In the domain of point cloud analysis, despite the significant capabilities of Graph Neural Networks (GNNs) in managing complex 3D datasets, existing approaches encounter challenges like high computational costs and scalability issues with…

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long…

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…

We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of attention function when calculating attention weights. Instead,…

We present a novel lightweight convolutional neural network for point cloud analysis. In contrast to many current CNNs which increase receptive field by downsampling point cloud, our method directly operates on the entire point sets without…

Short-term future population prediction is a crucial problem in urban computing. Accurate future population prediction can provide rich insights for urban planners or developers. However, predicting the future population is a challenging…

Airborne light detection and ranging (LiDAR) plays an increasingly significant role in urban planning, topographic mapping, environmental monitoring, power line detection and other fields thanks to its capability to quickly acquire…

Attention mechanisms have become a cornerstone in modern neural networks, driving breakthroughs across diverse domains. However, their application to graph structured data, where capturing topological connections is essential, remains…

3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object…

Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions…

Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect. The standard convolution characterises feature correspondences indistinguishably among 3D points, presenting an intrinsic…

The existing 3D deep learning methods adopt either individual point-based features or local-neighboring voxel-based features, and demonstrate great potential for processing 3D data. However, the point based models are inefficient due to the…

We introduce Position Adaptive Convolution (PAConv), a generic convolution operation for 3D point cloud processing. The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight…