Related papers: Region adaptive graph fourier transform for 3d poi…
We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks. Our network represents a 3D shape as a set of locality-preserving 1D ordered list of points at multiple…
Deep learning on the point cloud is increasingly developing. Grouping the point with its neighbors and conducting convolution-like operation on them can learn the local feature of the point cloud, but this method is weak to extract the…
LiDARs are widely used in autonomous robots due to their ability to provide accurate environment structural information. However, the large size of point clouds poses challenges in terms of data storage and transmission. In this paper, we…
In recent years, point clouds have become increasingly popular for representing three-dimensional (3D) visual objects and scenes. To efficiently store and transmit point clouds, compression methods have been developed, but they often result…
In conventional point cloud delivery, a sender uses octree-based digital video compression to stream three-dimensional (3D) points and the corresponding color attributes over band-limited links, e.g., wireless channels, for 3D scene…
We propose a new attention mechanism, called Global Hierarchical Attention (GHA), for 3D point cloud analysis. GHA approximates the regular global dot-product attention via a series of coarsening and interpolation operations over multiple…
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate complete point clouds with details. In this paper, we propose a novel point cloud completion network, namely CompleteDT. Specifically,…
Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…
With the proliferation of Lidar sensors and 3D vision cameras, 3D point cloud analysis has attracted significant attention in recent years. After the success of the pioneer work PointNet, deep learning-based methods have been increasingly…
Recent advances in deep learning for 3D point clouds have shown great promises in scene understanding tasks thanks to the introduction of convolution operators to consume 3D point clouds directly in a neural network. Point cloud data,…
This paper exploits Geometric (Clifford) Algebra (GA) theory in order to devise and introduce a new adaptive filtering strategy. From a least-squares cost function, the gradient is calculated following results from Geometric Calculus (GC),…
Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point clouds containing irregular neighborhoods constantly breaks…
Being able to learn an effective semantic representation directly on raw point clouds has become a central topic in 3D understanding. Despite rapid progress, state-of-the-art encoders are restrictive to canonicalized point clouds, and have…
Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds, and it is crucial for tasks such as 3D object detection and segmentation. Despite the continuous advances in point cloud analysis techniques,…
Point clouds are a basic data type that is increasingly of interest as 3D content becomes more ubiquitous. Applications using point clouds include virtual, augmented, and mixed reality and autonomous driving. We propose a more efficient…
Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including…
Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines. However, point cloud data is inherently sparse and irregular, causing significant difficulties for machine perception. In this work, we…
Unsupervised domain adaptation (UDA) aims to learn transferable representation across domains. Recently a few UDA works have successfully applied Transformer-based methods and achieved state-of-the-art (SOTA) results. However, it remains…
Graph fractional Fourier transform (GFRFT) is an extension of graph Fourier transform (GFT) that provides an additional fractional analysis tool for graph signal processing (GSP) by generalizing temporal-vertex domain Fourier analysis to…
One of the key challenges in the area of signal processing on graphs is to design transforms and dictionaries methods to identify and exploit structure in signals on weighted graphs. In this paper, we first generalize graph Fourier…