By Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun and Xin Tong.
Internet Graphics Group, Microsoft Research Asia.
This repository contains the implementation of O-CNN introduced in our Siggraph 2017 paper "O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis". The code is released under the MIT license.
If you use our code or models, please cite our paper.
@article {Wang-2017-OCNN,
title = {O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis},
author = {Wang, Peng-Shuai and Liu, Yang and Guo, Yu-Xiao and Sun, Chun-Yu and Tong, Xin},
journal = {ACM Transactions on Graphics (SIGGRAPH)},
volume = {36},
number = {4},
year = {2017},
}
O-CNN is built upon the Caffe framework and it supports octree-based convolution, deconvolution, pooling, and unpooling. The code has been tested on the Windows and Linux platforms (window 10 and Ubuntu 16.04), . Its installation is as follows:
- Clone Caffe with revision
6bfc5ca8f7c2a4b7de09dfe7a01cf9d3470d22b3
- The code for O-CNN is contained in the directory
caffe
. Clone and put it into the Caffe directory. - Follow the installation instructions of Caffe to build the code to get the executive files
caffe.exe
andconvert_octree_data.exe
etc.
Our O-CNN takes the octree representation of 3D objects as input. The efficient octree data structure is described in our paper. For convenience, we provide a reference implementation to convert the point cloud with oriented normal to our octree format. The code is contained in the directory octree
, along with the Microsoft Visual studio 2015 solution file, which can be built to obtain the executable file octree.exe
.
The experiments in our paper can be reproduced as follows.
For achieving better performance, we store all the octree inputs in a leveldb
or lmdb
database. Here are the details how to generate databases for O-CNN.
-
Download and unzip the corresponding 3D model dataset (like the ModelNet40 dataset) into a folder.
-
Convert all the models (in OBJ/OFF format) to dense point clouds with normals (in POINTS format). As detailed in our paper, we build a virtual scanner and shoot rays to calculate the intersection points and oriented normals. The executable files and source code can be downloaded here.
-
Run the tool
octree.exe
to convert point clouds into the octree files.Usage:
Octree <filelist> [depth] [full_layer] [displacement] [augmentation] [segmentation]
filelist: a text file whose each line specifies the full path name of a POINTS file
depth: the maximum depth of the octree tree
full_layer: which layer of the octree is full. suggested value: 2
displacement: the offset value for handing extremely thin shapes: suggested value: 0.5
segmentation: a boolean value indicating whether the output is for the segmentation task.
-
Convert all the octrees into a
lmdb
orleveldb
database by the toolconvert_octree_data.exe
.
The instruction how to run the shape classification experiment:
- Download the ModelNet40 dataset, and convert it to a
lmdb
database as described above. Here we provide almdb
database with 5-depth octrees for convenience. - Download the
O-CNN
protocol buffer files, which are contained in the foldercaffe/examples/o-cnn
. - Configure the path of the database and run
caffe.exe
according to the instructions of Caffe. We also provide our pre-trained Caffe model incaffe/examples/o-cnn
.
The instruction how to run the shape retrieval experiment:
- Download the dataset from SHREC16, and convert it to a
lmdb
database as described above. - Follow the same approach as the classification task to train the O-CNN.
- In the retrieval experiment, the orientation pooling is used to achieve better performance. The code
caffe/tools/feature_pooling.cpp
can be used to fulfill the task. We will provide the automated tool soon. - The retrieval result can be evaluated by the javascript code provided by SHREC16.
The instruction how to run the segmentation experiment:
- The original part annotation data is provided as the supplemental material of the work "A Scalable Active Framework for Region Annotation in 3D Shape Collections". As detailed in Section 5.3 of our paper, the point cloud in the original dataset is relatively sparse and the normal information is missing. We convert the sparse point clouds to dense points with normal information and correct part annotation. Here is one converted dataset for your convenience, and we will release more data soon.
- convert the dataset to a
lmdb
database. - Download the protocol buffer files, which are contained in the folder
caffe/examples/o-cnn
. - For CRF refinement, please refer to the code provided here. We will provide the automated tool soon.
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 problem about our implementation or request to access all the datasets.