From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments

• URL: http://arxiv.org/abs/2605.02098v1
• Date: Sun, 03 May 2026 23:36:32 GMT
• Title: From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments
• Abstract summary: Large-scale 3D point clouds can consist of billions of points.<n>In order to develop a semantic understanding of the scene, the point clouds are divided into smaller subclouds that can be processed.<n>We propose alternative methods that produce subclouds with larger crop sizes while maintaining a similar number of points.
• Score: 39.21200612994709
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale 3D point clouds can consist of billions of points. Even after downsampling, these point clouds are too large for modern 3D neural networks. In order to develop a semantic understanding of the scene, the point clouds are divided into smaller subclouds that can be processed. Typically, this division is done using spherical crops, resulting in a loss of surrounding geometric context. To address this issue, we propose alternative methods that produce subclouds with larger crop sizes while maintaining a similar number of points. Specifically, we compare exponential, Gaussian, and linear cropping methods with the spherical method. We evaluated two 3D deep learning model architectures using multiple indoor and outdoor environment datasets. Our results demonstrate that altering the cropping strategy can enhance model performance, especially for large-scale outdoor scenes, yielding new state-of-the-art results. Code is available at https://github.com/mvg-inatech/point_cloud_cropping

Related papers

• DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classification [10.744510913722817]
  Deep neural networks have achieved significant success in 3D point cloud classification.<n>In this paper, we focus on the 3D point cloud domain generalization problem.<n>We propose a novel method for 3D point cloud domain generalization, which can generalize to unseen domains of point clouds.
  arXiv  Detail & Related papers  (2025-04-16T19:43:32Z)
• Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding [11.416392706435415]
  Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs) Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking the inherent and expressible point cloud geometric structure. We introduce the first training-free aggregation technique that leverages the point cloud's 3D geometric structure to improve the quality of the transferred Vision-Language Models.
  arXiv  Detail & Related papers  (2023-12-04T12:30:07Z)
• CurveCloudNet: Processing Point Clouds with 1D Structure [49.137477909835276]
  We introduce a new point cloud processing scheme and backbone, called CurveCloudNet. CurveCloudNet parameterizes the point cloud as a collection of polylines, establishing a local surface-aware ordering on the points. We demonstrate that CurveCloudNet outperforms both point-based and sparse-voxel backbones in various segmentation settings.
  arXiv  Detail & Related papers  (2023-03-21T17:41:36Z)
• PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priors [25.569519066857705]
  We propose a new method for mapping a 3D point cloud to the latent space of a 3D generative adversarial network. Our method outperforms previous GAN inversion methods for 3D point clouds.
  arXiv  Detail & Related papers  (2022-11-16T06:29:29Z)
• POCO: Point Convolution for Surface Reconstruction [92.22371813519003]
  Implicit neural networks have been successfully used for surface reconstruction from point clouds. Many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. We propose to use point cloud convolutions and compute latent vectors at each input point.
  arXiv  Detail & Related papers  (2022-01-05T21:26:18Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• Learning Gradient Fields for Shape Generation [69.85355757242075]
  A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. We generate point clouds by performing gradient ascent on an unnormalized probability density. Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted from score-based generative models.
  arXiv  Detail & Related papers  (2020-08-14T18:06:15Z)
• Learning to Segment 3D Point Clouds in 2D Image Space [20.119802932358333]
  We show how to efficiently project 3D point clouds into a 2D image space. Traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation.
  arXiv  Detail & Related papers  (2020-03-12T03:18:59Z)
• PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling [103.09504572409449]
  We propose a novel deep neural network based method, called PUGeo-Net, to generate uniform dense point clouds. Thanks to its geometry-centric nature, PUGeo-Net works well for both CAD models with sharp features and scanned models with rich geometric details.
  arXiv  Detail & Related papers  (2020-02-24T14:13:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.