Related papers: PCPNet: An Efficient and Semantic-Enhanced Transfo…

In this paper, we present the PS^2-Net -- a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds. In order to deeply incorporate local structures and global context to support 3D scene…

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)…

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…

We study a new problem of semantic complete scene forecasting (SCSF) in this work. Given a 4D dynamic point cloud sequence, our goal is to forecast the complete scene corresponding to the future next frame along with its semantic labels. To…

In this paper, we introduce a deep encoder-decoder network, named SalsaNet, for efficient semantic segmentation of 3D LiDAR point clouds. SalsaNet segments the road, i.e. drivable free-space, and vehicles in the scene by employing the…

With the tide of artificial intelligence, we try to apply deep learning to understand 3D data. Point cloud is an important 3D data structure, which can accurately and directly reflect the real world. In this paper, we propose a simple and…

The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedforward, and high-level information is rarely reused to…

Understanding and predicting video content is essential for planning and reasoning in dynamic environments. Despite advancements, unsupervised learning of object representations and dynamics remains challenging. We present VideoPCDNet, an…

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will…

Semantic segmentation is an important component in the perception systems of autonomous vehicles. In this work, we adopt recent advances in both image and point cloud segmentation to achieve a better accuracy in the task of segmenting LiDAR…

Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we take a step towards more discriminative 3D point cloud…

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…

We present a technique for visualizing point clouds using a neural network. Our technique allows for an instant preview of any point cloud, and bypasses the notoriously difficult surface reconstruction problem or the need to estimate…

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use…

Despite the recent development of deep learning-based point cloud upsampling, most MLP-based point cloud upsampling methods have limitations in that it is difficult to train the local and global structure of the point cloud at the same…

Despite recent success in incorporating learning into point cloud registration, many works focus on learning feature descriptors and continue to rely on nearest-neighbor feature matching and outlier filtering through RANSAC to obtain the…

Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fully leverage global and local semantic information for…

Predicting the dynamics of complex systems is crucial for various scientific and engineering applications. The accuracy of predictions depends on the model's ability to capture the intrinsic dynamics. While existing methods capture key…

We present a novel deep learning framework for flow field predictions in irregular domains when the solution is a function of the geometry of either the domain or objects inside the domain. Grid vertices in a computational fluid dynamics…