/O-CNN

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

Primary LanguageC++MIT LicenseMIT

O-CNN

This repository contains the implementation of O-CNN and Adaptive O-CNN introduced in our SIGGRAPH 2017 paper and SIGGRAPH Asia 2018 paper.
The code is released under the MIT license.

If you use our code or models, please cite our paper.

What's New?

  • 2020.08.16: We released our code for 3D unsupervised learning. We provided a unified network architecture for generic shape analysis tasks and an unsupervised method to pretrain the network. Our method achieved state-of-the-art performance on several benchmarks.
  • 2020.08.12: We released our code for Partnet segmentation. We achieved an average IoU of 58.4, significantly better than PointNet (IoU: 35.6), PointNet++ (IoU: 42.5), SpiderCNN (IoU: 37.0), and PointCNN(IoU: 46.5).
  • 2020.08.05: We released our code for shape completion. We proposed a simple yet efficient network and output-guided skip connections for 3D completion, which achieved state-of-the-art performances on several benchmarks.
  • 2020.03.16: We released ResNet-based O-CNN architecture for shape classification. We achieved a testing accuracy of 92.5 on ModelNet40 (without voting).

Contents

We thank the authors of ModelNet, ShapeNet and Region annotation dataset for sharing their 3D model datasets with the public.

Please contact us (Pengshuai Wang wangps@hotmail.com, Yang Liu yangliu@microsoft.com ) if you have any problems about our implementation.