改进点云裁剪方法，提升大场景3D模型性能。
From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments
- 用高斯、指数等新裁剪方式替代传统球形裁剪。
- 在户外大场景中显著提升模型精度，达新SOTA。
- 适合做大规模3D感知与场景理解的研究者。
大规模3D点云可包含上亿个点，即使下采样后仍过大，难以直接输入现代3D神经网络。为实现场景语义理解，需将点云分割为可处理的子云。传统方法采用球形裁剪，但会损失周围几何上下文。为此，本文提出新型裁剪策略，可在保持点数相近的前提下扩大裁剪范围，对比了指数、高斯与线性裁剪与球形裁剪的差异。在多个室内与室外数据集上评估了三种3D深度学习模型架构，结果表明改变裁剪策略能显著提升模型表现，尤其在大尺度户外场景中取得新的最先进成果。代码已开源：https://github.com/mvg-inatech/point_cloud_cropping。
原文摘要 · Abstract (English)
Large-scale 3D point clouds can consist of hundreds of millions 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 three 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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。