Related papers: Using a Waffle Iron for Automotive Point Cloud Sem…

Current state-of-the-art point cloud-based perception methods usually rely on large-scale labeled data, which requires expensive manual annotations. A natural option is to explore the unsupervised methodology for 3D perception tasks.…

High quality upsampling of sparse 3D point clouds is critically useful for a wide range of geometric operations such as reconstruction, rendering, meshing, and analysis. In this paper, we propose a data-driven algorithm that enables an…

Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the…

In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer vision is mainly driven by the pre-training on large-scale datasets…

Adapting deep learning networks for point cloud data recognition in self-driving vehicles faces challenges due to the variability in datasets and sensor technologies, emphasizing the need for adaptive techniques to maintain accuracy across…

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists)…

With recent success of deep learning in 2D visual recognition, deep learning-based 3D point cloud analysis has received increasing attention from the community, especially due to the rapid development of autonomous driving technologies.…

Unlike on images, semantic learning on 3D point clouds using a deep network is challenging due to the naturally unordered data structure. Among existing works, PointNet has achieved promising results by directly learning on point sets.…

Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…

Most point cloud compression methods operate in the voxel or octree domain which is not the original representation of point clouds. Those representations either remove the geometric information or require high computational power for…

We present a novel algorithm for point cloud segmentation. Our approach transforms unstructured point clouds into regular voxel grids, and further uses a kernel-based interpolated variational autoencoder (VAE) architecture to encode the…

The analyses relying on 3D point clouds are an utterly complex task, often involving million of points, but also requiring computationally efficient algorithms because of many real-time applications; e.g. autonomous vehicle. However, point…

3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging…

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point clouds, and…

Efficient transmission of 3D point cloud data is critical for advanced perception in centralized and decentralized multi-agent robotic systems, especially nowadays with the growing reliance on edge and cloud-based processing. However, the…

Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point…

Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D…

It is a crucial step to achieve effective semantic segmentation of lane marking during the construction of the lane level high-precision map. In recent years, many image semantic segmentation methods have been proposed. These methods mainly…