arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.06734cs.CV
收藏

用于点云分类和分割的高分辨率网络

Dense-Resolution Network for Point Cloud Classification and Segmentation

Australian National University(澳大利亚国立大学);Data61-CSIRO(联邦科学与工业研究组织Data61)

Shi Qiu, Saeed Anwar, Nick Barnes

摘要:

点云分析在机器人、增强现实、自动驾驶等领域有着广泛的应用前景,是人工智能研究的热点。然而,由于不规则性、无序性和稀疏性,它总是具有挑战性。在这篇文章中,我们提出了一种新的网络称为密集分辨率网络(DRNet)的点云分析。我们的DRNet旨在从不同分辨率的点云中学习局部点特征。为了更有效地学习局部点群,我们提出了一种新的局部邻域搜索分组方法和一个错误最小化模块捕获局部特征。除了在广泛使用的点云分割和分类基准上验证网络外,我们还测试和可视化组件的性能。与其他最先进的方法相比,我们的网络在ModelNet40,ShapeNet合成和ScanObjectNN真实点云数据集上显示出优越性。

英文摘要:

Point cloud analysis is attracting attention from Artificial Intelligence research since it can be widely used in applications such as robotics, Augmented Reality, self-driving. However, it is always challenging due to irregularities, unorderedness, and sparsity. In this article, we propose a novel network named Dense-Resolution Network (DRNet) for point cloud analysis. Our DRNet is designed to learn local point features from the point cloud in different resolutions. In order to learn local point groups more effectively, we present a novel grouping method for local neighborhood searching and an error-minimizing module for capturing local features. In addition to validating the network on widely used point cloud segmentation and classification benchmarks, we also test and visualize the performance of the components. Comparing with other state-of-the-art methods, our network shows superiority on ModelNet40, ShapeNet synthetic and ScanObjectNN real point cloud datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑