点云深度学习的Pytorch框架

这是3D 点云的深度学习框架，提供常见的点云分析方法的一种通用深度学习模型。它主要依赖Pytorch Geometric和Facebook Hydra。该框架能够以最小的代价和极大的可重复性来构建精简而复杂的模型。目标是建立一个工具，用于对SOTA模型进行基准测试，同时允许研究者们有效地研究点云分析，最终目标是建立可应用于实际应用的模型。

代码已经开源 https://github.com/nicolas-chaulet/torch-points3d（最近似乎又更新了）

工程结构

作为一种函数库，所以必然提供了一些常见的深度学习算法和接口，并且按任务划分模型和数据集。支持分割，分类和配准。

支持的数据集

分割的数据集：

* Scannet from Angela Dai et al.: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

* S3DIS from Iro Armeni et al.: Joint 2D-3D-Semantic Data for Indoor Scene Understanding

* Shapenet from Iro Armeni et al.: ShapeNet: An Information-Rich 3D Model Repository

分类的数据集：

* ModelNet from Zhirong Wu et al.: 3D ShapeNets: A Deep Representation for Volumetric Shapes

配准的数据集：

* 3DMatch from Andy Zeng et al.: 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

依赖项

* CUDA > 10

* Python 3 + headers (python-dev)

* Poetry (Optional but highly recommended)

使用以及安装教程

https://torch-points3d.readthedocs.io/en/latest/src/gettingstarted.html

已经实现的深度学习相关的文章

* PointNet from Charles R. Qi et al.: PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017)

* PointNet++ from Charles from Charles R. Qi et al.: PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

* RSConv from Yongcheng Liu et al.: Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019)

* RandLA-Net from Qingyong Hu et al.: RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

* PointCNN from Yangyan Li et al.: PointCNN: Convolution On X-Transformed Points (NIPS 2018)

* KPConv from Hugues Thomas et al.: KPConv: Flexible and Deformable Convolution for Point Clouds (ICCV 2019)

* MinkowskiEngine from Christopher Choy et al.: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks (CVPR'19)