论文标题
点云的表面表示
Surface Representation for Point Clouds
论文作者
论文摘要
大多数先前的工作代表了坐标的点云的形状。但是，直接描述局部几何形状是不足的。在本文中，我们提出\ textbf {repsurf}（代表性表面），这是\ textbf {explacicitly}的点云的新颖表示形式描述了非常局部的结构。我们探索了repsurf，三角形repsurf和雨伞repsurf的两个变体，这些变体灵感来自计算机图形中的三角网格和伞曲率。我们在表面重建后通过预定义的几何先验计算Repsurf的表示。由于其与不规则积分的免费协作，Repsurf可以成为大多数点云模型的插件模块。基于PointNet ++（SSG版本）的简单基线，雨伞Repsurf在性能和效率方面，通过大量的分类，细分和检测来超过先前的最新时间。随着参数数量的增加\ textbf {0.008m}，\ textbf {0.04g} flops和\ textbf {1.12ms}推理时间，我们的方法在模型Net40和text40和textbf {84。Actieves \ textbf {94.7 \％}（+0.5 \％）上（+1.8 \％）在scanobjectnn上进行分类，而\ textbf {74.3 \％}（+0.8 \％）miou在S3DIS上为6倍6倍，\ textbf {70.0 \％}（+1.6 \％）miou在Scannet上进行了scannet for Chessecation。为了检测，我们的repurf先前的先前最先进的检测器获得了\ textbf {71.2 \％}（+2.1 \％）映射$ \ mathit {_ {25}} $，\ textbf {54.8 \％}（+2.0 \％}（+2.0 \％） \ textbf {64.9 \％}（+1.9 \％）地图$ \ mathit {_ {25}} $，\ textbf {47.7 \％}（+2.5 \％）map $ \ mathit {_ _ {_ {50}} $在Sun Rgb-d上。我们轻巧的三角形狂欢也在这些基准测试中表现出色。该代码可在\ url {https://github.com/hancyran/repsurf}上公开获得。
Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present \textbf{RepSurf} (representative surfaces), a novel representation of point clouds to \textbf{explicitly} depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around \textbf{0.008M} number of parameters, \textbf{0.04G} FLOPs, and \textbf{1.12ms} inference time, our method achieves \textbf{94.7\%} (+0.5\%) on ModelNet40, and \textbf{84.6\%} (+1.8\%) on ScanObjectNN for classification, while \textbf{74.3\%} (+0.8\%) mIoU on S3DIS 6-fold, and \textbf{70.0\%} (+1.6\%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains \textbf{71.2\%} (+2.1\%) mAP$\mathit{_{25}}$, \textbf{54.8\%} (+2.0\%) mAP$\mathit{_{50}}$ on ScanNetV2, and \textbf{64.9\%} (+1.9\%) mAP$\mathit{_{25}}$, \textbf{47.7\%} (+2.5\%) mAP$\mathit{_{50}}$ on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at \url{https://github.com/hancyran/RepSurf}.
