Related papers: Nearest Neighbors Meet Deep Neural Networks for Po…

Point cloud data has been extensively studied due to its compact form and flexibility in representing complex 3D structures. The ability of point cloud data to accurately capture and represent intricate 3D geometry makes it an ideal choice…

Since the PointNet was proposed, deep learning on point cloud has been the concentration of intense 3D research. However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point…

Recently, deep reinforcement learning (RL) has achieved remarkable empirical success by integrating deep neural networks into RL frameworks. However, these algorithms often require a large number of training samples and admit little…

In this paper, we propose a point cloud classification method based on graph neural network and manifold learning. Different from the conventional point cloud analysis methods, this paper uses manifold learning algorithms to embed point…

Nonparametric learning is a fundamental concept in machine learning that aims to capture complex patterns and relationships in data without making strong assumptions about the underlying data distribution. Owing to simplicity and…

k-nearest neighbor (k-NN) search is a fundamental primitive in geometry processing and computer graphics. While spatial partitioning structures such as kd-trees are standard, they are often manifold-blind, failing to exploit the intrinsic…

Convolutional neural networks (CNNs) have become a key asset to most of fields in AI. Despite their successful performance, CNNs suffer from a major drawback. They fail to capture the hierarchy of spatial relation among different parts of…

Recent medical image reconstruction techniques focus on generating high-quality medical images suitable for clinical use at the lowest possible cost and with the fewest possible adverse effects on patients. Recent works have shown…

Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes. Yet, this adaptability is vital for addressing user data privacy concerns. We address this limitation by storing…

This paper introduces a new method for 3D point cloud registration based on deep learning. The architecture is composed of three distinct blocs: (i) an encoder composed of a convolutional graph-based descriptor that encodes the immediate…

Deep Neural Networks (DNNs) have improved the accuracy of classification problems in lots of applications. One of the challenges in training a DNN is its need to be fed by an enriched dataset to increase its accuracy and avoid it suffering…

3D object detection is an essential vision technique for various robotic systems, such as augmented reality and domestic robots. Transformers as versatile network architectures have recently seen great success in 3D point cloud object…

Steering estimation is a critical task in autonomous driving, traditionally relying on 2D image-based models. In this work, we explore the advantages of incorporating 3D spatial information through hybrid architectures that combine 3D…

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…

We propose a novel approach aimed at object and semantic scene completion from a partial scan represented as a 3D point cloud. Our architecture relies on three novel layers that are used successively within an encoder-decoder structure and…

A $k$-nearest neighbor ($k$NN) query determines the $k$ nearest points, using distance metrics, from a specific location. An all $k$-nearest neighbor (A$k$NN) query constitutes a variation of a $k$NN query and retrieves the $k$ nearest…

We show the sup-norm convergence of deep neural network estimators with a novel adversarial training scheme. For the nonparametric regression problem, it has been shown that an estimator using deep neural networks can achieve better…

Recent works have theoretically and empirically shown that deep neural networks (DNNs) have an inherent vulnerability to small perturbations. Applying the Deep k-Nearest Neighbors (DkNN) classifier, we observe a dramatically increasing…

When 3D-point clouds from overhead sensors are used as input to remote sensing data exploitation pipelines, a large amount of effort is devoted to data preparation. Among the multiple stages of the preprocessing chain, estimating the…

The joint hyperspectral image (HSI) and LiDAR data classification aims to interpret ground objects at more detailed and precise level. Although deep learning methods have shown remarkable success in the multisource data classification task,…