Related papers: Over-the-Air Learning-based Geometry Point Cloud T…

Graph Network Simulators (GNSs) have emerged as powerful surrogates for complex physics-based simulation, offering inherent differentiability and orders-of-magnitude speedups over traditional solvers. However, GNSs typically assume access…

Over-the-air federated learning (OTA-FL) offers an exciting new direction over classical FL by averaging model weights using the physics of analog signal propagation. Since each participant broadcasts its model weights concurrently in time…

Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking…

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…

We proposed a novel graph convolutional neural network that could construct a coarse, sparse latent point cloud from a dense, raw point cloud. With a novel non-isotropic convolution operation defined on irregular geometries, the model then…

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most…

Point cloud is one of the widely used techniques for representing and storing 3D geometric data. In the past several methods have been proposed for processing point clouds. Methods such as PointNet and FoldingNet have shown promising…

High-efficient image compression is a critical requirement. In several scenarios where multiple modalities of data are captured by different sensors, the auxiliary information from other modalities are not fully leveraged by existing…

Point cloud segmentation is one of the most important tasks in computer vision with widespread scientific, industrial, and commercial applications. The research thereof has resulted in many breakthroughs in 3D object and scene…

We propose a novel normal estimation method called HSurf-Net, which can accurately predict normals from point clouds with noise and density variations. Previous methods focus on learning point weights to fit neighborhoods into a geometric…

Spiking Neural Networks (SNNs) offer an attractive and energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their sparse binary activation. When SNN meets Transformer, it shows great potential in 2D image…

Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is…

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named…

LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention)…

The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns. Conventional point-based models exploit local patterns through a symmetric function (e.g. max pooling)…

Point cloud compression has garnered significant interest in computer vision. However, existing algorithms primarily cater to human vision, while most point cloud data is utilized for machine vision tasks. To address this, we propose a…

Using 3D point clouds in odometry estimation in robotics often requires finding a set of correspondences between points in subsequent scans. While there are established methods for point clouds of sufficient quality, state-of-the-art still…

In this paper, we propose an end-to-end learning network to predict future frames in a point cloud sequence. As main novelty, an initial layer learns topological information of point clouds as geometric features, to form representative…

In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation matches intrinsic characteristics of point clouds: the number of…

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…