Related papers: PLATYPUS: Progressive Local Surface Estimator for …
Accurate 3D scene understanding in outdoor environments heavily relies on high-quality point clouds. However, LiDAR-scanned data often suffer from extreme sparsity, severely hindering downstream 3D perception tasks. Existing point cloud…
Existing learning-based point cloud upsampling methods often overlook the intrinsic data distribution charac?teristics of point clouds, leading to suboptimal results when handling sparse and non-uniform point clouds. We propose a novel…
Learning 3D scene flow from LiDAR point clouds presents significant difficulties, including poor generalization from synthetic datasets to real scenes, scarcity of real-world 3D labels, and poor performance on real sparse LiDAR point…
In recent years new application areas have emerged in which one aims to capture the geometry of objects by means of three-dimensional point clouds. Often the obtained data consist of a dense sampling of the object's surface, containing many…
Point cloud downsampling is a crucial pre-processing operation to downsample points in order to unify data size and reduce computational cost, to name a few. Recent research on point cloud downsampling has achieved great success which…
Point cloud sampling is a less explored research topic for this data representation. The most commonly used sampling methods are still classical random sampling and farthest point sampling. With the development of neural networks, various…
We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral…
In the context of Intelligent Transportation Systems (ITS), efficient data compression is crucial for managing large-scale point cloud data acquired by roadside LiDAR sensors. The demand for efficient storage, streaming, and real-time…
Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in…
In this paper, we propose a normal estimation method for unstructured 3D point clouds. In this method, a feature constraint mechanism called Local Plane Features Constraint (LPFC) is used and then a multi-scale selection strategy is…
Recent advances in generative modeling have demonstrated strong promise for high-quality point cloud upsampling. In this work, we present PUFM++, an enhanced flow-matching framework for reconstructing dense and accurate point clouds from…
The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Recent state-of-the-art methods have relatively complex architectures such as…
Current methodologies in point cloud analysis predominantly explore 3D geometries, often achieved through the introduction of intricate learnable geometric extractors in the encoder or by deepening networks with repeated blocks. However,…
Extracting high-level structural information from 3D point clouds is challenging but essential for tasks like urban planning or autonomous driving requiring an advanced understanding of the scene at hand. Existing approaches are still not…
3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks (DNNs) have achieved remarkable success in…
We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rendering, collision avoidance for planning, animation, etc.…
Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces. Another key challenge lies in reducing decoding latency, a…
We study the problem of self-supervised 3D scene flow estimation from real large-scale raw point cloud sequences, which is crucial to various tasks like trajectory prediction or instance segmentation. In the absence of ground truth scene…
Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the…
Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved…