Skip to content

This is the implementation of Recycle Maxpooling Module for Point Cloud Analysis

Notifications You must be signed in to change notification settings

jiajingchen113322/Recycle_Maxpooling_Module

Repository files navigation

Recycling Max Pooling Module for 3D Point Cloud Analysis (CVPR2022)

This is a pytorch implementation of the paper: Why Discard if You can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis. The paper could be found here. For a quick learning, you could go to /model/cls or /model/seg to compare the original DGCNN and DGCNN with RMP for classification and segmentation task. The code for ScanObjectNN, ModelNet40 and S3DIS dataset experiment has been given, I will finish the code instruction of ScanObjectNN and S3DIS as soon as possible.

Recycle Max Pooling Module

The picture below shows the network structure of point-based method. Most point-based method use max pooling module to extract Permutation Invaraint Feature for downstream task. However, according to our abservation, a great number of points are completely discarded during the max pooling. image width="100" height="100"

In order to solve this problem, we proposed the Recycling Max Pooling Module to make use of the discarded points' feature, which is shown below: image width="100" height="100"
For more details, please refer to the paper

Point Cloud Classification on ModelNet40

You can download the official data, and unzip it. The path of "Data" is needed for traning.

Train

Training the original DGCNN

python main_modelnet40.py --data_path /path/to/Data --exp_name DGCNN

Training the DGCNN with RMP(Recycling Max Pooling)

python main_modelnet40_ref.py --data_path /path/to/Data --exp_name DGCNN_RMP

Evaluation is performed after each epoch's training. You could check the accuracy by

tensorboard --logdir /path/to/the/experiment

About

This is the implementation of Recycle Maxpooling Module for Point Cloud Analysis

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages