Related papers: LAHNet: Local Attentive Hashing Network for Point …

Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space. The correspondence problem is generally addressed by the design of discriminative 3D local descriptors on the…

Environment perception including detection, classification, tracking, and motion prediction are key enablers for automated driving systems and intelligent transportation applications. Fueled by the advances in sensing technologies and…

We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well…

Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data.…

For current object detectors, the scale of the receptive field of feature extraction operators usually increases layer by layer. Those operators are called scale-oriented operators in this paper, such as the convolution layer in CNN, and…

Pooling layers (e.g., max and average) may overlook important information encoded in the spatial arrangement of pixel intensity and/or feature values. We propose a novel lacunarity pooling layer that aims to capture the spatial…

LiDAR-based place recognition is one of the key components of SLAM and global localization in autonomous vehicles and robotics applications. With the success of DL approaches in learning useful information from 3D LiDARs, place recognition…

Point clouds have grown in importance in the way computers perceive the world. From LIDAR sensors in autonomous cars and drones to the time of flight and stereo vision systems in our phones, point clouds are everywhere. Despite their…

We propose a novel framework to learn 3D point cloud semantics from 2D multi-view image observations containing pose error. On the one hand, directly learning from the massive, unstructured and unordered 3D point cloud is computationally…

This paper proposes EyeNet, a novel semantic segmentation network for point clouds that addresses the critical yet often overlooked parameter of coverage area size. Inspired by human peripheral vision, EyeNet overcomes the limitations of…

Low-overlap regions between paired point clouds make the captured features very low-confidence, leading cutting edge models to point cloud registration with poor quality. Beyond the traditional wisdom, we raise an intriguing question: Is it…

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global…

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…

Remarkable advancements have been made recently in point cloud analysis through the exploration of transformer architecture, but it remains challenging to effectively learn local and global structures within point clouds. In this paper, we…

Rigid registration of point clouds is a fundamental problem in computer vision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, conventional methods like…

Point cloud registration plays a crucial role in various computer vision tasks, and usually demands the resolution of partial overlap registration in practice. Most existing methods perform a serial calculation of rotation and translation,…

Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadratically with the spatial resolution. A series of works…

In recent years, significant progress has been made on the research of crowd counting. However, as the challenging scale variations and complex scenes existed in crowds, neither traditional convolution networks nor recent Transformer…

We tackle the problem of localizing 3D point cloud submaps using complex and diverse natural language descriptions, and present Text2Loc++, a novel neural network designed for effective cross-modal alignment between language and point…

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…