Point-GR通过图残差结构提升点云分类与分割性能，参数更少、效果更强。
Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation
- 设计图残差网络，解决点云无序性带来的特征失真问题。
- 在S3DIS数据集上达73.47%平均IoU，超越现有方法。
- 参数量更低，适合资源受限场景下的3D点云分析。
近年来，点云数据中的3D形状分析在计算机视觉领域受到广泛关注。如何有效表示3D信息并提取有意义的特征，仍是分类任务中的关键挑战。本文提出Point-GR，一种专为将无序原始点云映射到高维空间而设计的深度学习架构，同时保留局部几何特征。该网络引入基于残差的学习机制，缓解点云数据中的点排列问题。相较于基线图神经网络，Point-GR在分类与部分分割任务中显著减少了网络参数数量。尤其在S3DIS基准数据集上，该模型实现了73.47%的场景分割平均IoU，展现了卓越性能。此外，其在分类与部分分割任务中也表现优异。
原文摘要 · Abstract (English)
In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for classification tasks remains crucial. This paper presents Point-GR, a novel deep learning architecture designed explicitly to transform unordered raw point clouds into higher dimensions while preserving local geometric features. It introduces residual-based learning within the network to mitigate the point permutation issues in point cloud data. The proposed Point-GR network significantly reduced the number of network parameters in Classification and Part-Segmentation compared to baseline graph-based networks. Notably, the Point-GR model achieves a state-of-the-art scene segmentation mean IoU of 73.47% on the S3DIS benchmark dataset, showcasing its effectiveness. Furthermore, the model shows competitive results in Classification and Part-Segmentation tasks.
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。