Home

Awesome

A Closer Look at Local Aggregation Operators in Point Cloud Analysis

By Ze Liu, Han Hu, Yue Cao, Zheng Zhang, Xin Tong

Updates

Introduction

This repo is the official implementation of "A Closer Look at Local Aggregation Operators in Point Cloud Analysis", which provides clean and the best (to-date) implementations for several representative operators including, Point MLP based (PointNet++-Like), Pseudo Grid based (KPConv-Like) and Adapt Weights (ContinuousConv-Like). It also includes a new family of local aggregation operators without learnable weights, named Position Pooling (PosPool), which is simpler than previous operators but performs similarly well or slightly better. Both PyTorch and TensorFlow implementations are given.

Three datasets are tested, including ModelNet, S3DIS and PartNet. Our implementations all achieve (or are close to) the state-of-the-art accuracy on these benchmarks by proper configurations of each operator type. In particular, one settings achieves 53.8 part category mean IoU on PartNet test set, which outperforms previous best implementations by 7.4 mIoU.

Citation

@article{liu2020closerlook3d,
  title={A Closer Look at Local Aggregation Operators in Point Cloud Analysis},
  author={Liu, Ze and Hu, Han and Cao, Yue and Zhang, Zheng and Tong, Xin},
  journal={ECCV},
  year={2020}
}

Main Results

ModelNet40

MethodAccTensorflow ModelPytorch Model
Point-wise MLP92.8Google / Baidu(wquw)Google / Baidu(fj13)
Pseudo Grid93.0Google / Baidu(lvw4)Google / Baidu(gmh5)
Adapt Weights93.0Google / Baidu(6zrg)Google / Baidu(bbus)
PosPool92.9Google / Baidu(pkzd)Google / Baidu(wuuv)
PosPool*93.2Google / Baidu(mjb1)Google / Baidu(qcc6)

S3DIS

MethodmIoUTensorflow ModelPytorch Model
Point-wise MLP66.2Google / Baidu(4mhy)Google / Baidu(53as)
Pseudo Grid65.9Google / Baidu(06ta)Google / Baidu(8skn)
Adapt Weights66.5Google / Baidu(7w43)Google / Baidu(b7zv)
PosPool66.5Google / Baidu(gqqe)Google / Baidu(z752)
PosPool*66.7Google / Baidu(qtkw)Google / Baidu(r96f)

PartNet

MethodmIoU (val)mIoU (test)Tensorflow ModelPytorch Model
Point-wise MLP48.151.2Google / Baidu(zw15)Google / Baidu(wxff)
Pseudo Grid50.853.0Google / Baidu(0mtr)Google / Baidu(n6b7)
Adapt Weights50.153.5Google / Baidu(551l)Google / Baidu(pc22)
PosPool50.053.4Google / Baidu(rb4x)Google / Baidu(3qv5)
PosPool*50.653.8Google / Baidu(2ts3)Google / Baidu(czyq)

ShapeNetPart

MethodmIoUmsIoUAccPytorch Model
Point-wise MLP85.784.194.5Google / Baidu(mi2m)
Pseudo Grid86.084.394.6Google / Baidu(wde6)
Adapt Weights85.984.594.6Google / Baidu(dy1k)
PosPool85.984.694.6Google / Baidu(r2tr)
PosPool*86.284.894.8Google / Baidu(27ie)

Notes:

Install

Acknowledgements

Our tensorflow codes borrowed a lot from KPCONV.

License

The code is released under MIT License (see LICENSE file for details).