OpenPoints is a library built for fairly benchmarking and easily reproducing point-based methods for point cloud understanding. It is born in the course of PointNeXt project and is used as an engine therein.

OpenPoints currently supports reproducing the following models:

• PointNet
• DGCNN
• DeepGCN
• PointNet++
• ASSANet
• PointMLP
• PointNeXt

1. Extensibility: supports many representative networks for point cloud understanding, such as PointNet, DGCNN, DeepGCN, PointNet++, ASSANet, PointMLP, and our PointNeXt. More networks can be built easily based on our framework since OpenPoints support a wide range of basic operations including graph convolutions, self-attention, farthest point sampling, ball query, e.t.c.

2. Ease of Use: Build model, optimizer, scheduler, loss function, and data loader easily from cfg. Train and validate different models on various tasks by simply changing the cfg\*\*.yaml file.

   model = build_model_from_cfg(cfg.model)
   criterion = build_criterion_from_cfg(cfg.criterion)
   

OpenPoints only serves as an engine. Please refer to PointNeXt for a specific example of how to use and install

• [ ] pip install support
• [ ] clean code for shapenetpart
• [ ] more models

If you use this library, please kindly acknowledge our work:

@Article{qian2022pointnext,
  author  = {Qian, Guocheng and Li, Yuchen and Peng, Houwen and Mai, Jinjie and Hammoud, Hasan and Elhoseiny, Mohamed and Ghanem, Bernard},
  journal = {arXiv:2206.04670},
  title   = {PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies},
  year    = {2022},
}