Being able to learn an effective semantic representation directly on raw point clouds has become a central topic in 3D understanding. Despite rapid progress, state-of-the-art encoders are restrictive to canonicalized point clouds, and have weaker than necessary performance when encountering geometric transformation distortions. To overcome this challenge, we propose PointTree, a general-purpose point cloud encoder that is robust to transformations based on relaxed K-D trees. Key to our approach is the design of the division rule in K-D trees by using principal component analysis (PCA). We use the structure of the relaxed K-D tree as our computational graph, and model the features as border descriptors which are merged with pointwise-maximum operation. In addition to this novel architecture design, we further improve the robustness by introducing pre-alignment -- a simple yet effective PCA-based normalization scheme. Our PointTree encoder combined with pre-alignment consistently outperforms state-of-the-art methods by large margins, for applications from object classification to semantic segmentation on various transformed versions of the widely-benchmarked datasets. Code and pre-trained models are available at https://github.com/immortalCO/PointTree.
翻译:能够直接在原始云层上学习有效的语义表达法已经成为三维理解的一个中心议题。 尽管取得了迅速的进展, 最先进的编码器对卡通点云有限制性, 在遇到几何变形扭曲时, 其性能比必要的要弱。 为了克服这一挑战, 我们提议PointTree, 即一个通用点云编码器, 对基于放松的K- D 树的变形具有强大的功能。 我们的方法的关键是通过主要组成部分分析( PCA) 设计K- D 树的分解规则。 我们使用放松的 K- D 树的结构作为我们的计算图, 并将这些特征建模作为边界描述器, 与点对点最大操作合并。 除了这个新的结构设计外, 我们通过引入前对齐( 一个简单而有效的基于五氯苯的正规化计划) 来进一步提高稳健健健健性。 我们的方法的关键是使用大边距, 设计K- D 树的分解规则, 从对象分类到各种变换版模型的语义分解, 以及 http- bregres prem- prembregetal codeal mode am- dataset