Octree-based Sparse Convolutional Neural Networks
Project description
O-CNN
This repository contains the pure PyTorch-based implementation of
O-CNN. The code has been tested with
Pytorch>=1.6.0
, and Pytorch>=1.9.0
is preferred.
O-CNN is an octree-based sparse convolutional neural network framework for 3D
deep learning. O-CNN constrains the CNN storage and computation into non-empty
sparse voxels for efficiency and uses the octree
data structure to organize
and index these sparse voxels.
The concept of sparse convolution in O-CNN is the same with
H-CNN,
SparseConvNet,
and
MinkowskiNet.
The key difference is that our O-CNN uses the octree
to index the sparse
voxels, while these 3 works use the Hash Table
.
Our O-CNN is published in SIGGRAPH 2017, H-CNN is published in TVCG 2018, SparseConvNet is published in CVPR 2018, and MinkowskiNet is published in CVPR 2019. Actually, our O-CNN was submitted to SIGGRAPH in the end of 2016 and was officially accepted in March, 2017. The camera-ready version of our O-CNN was submitted to SIGGRAPH in April, 2017. We just did not post our paper on Arxiv during the review process of SIGGRAPH. Therefore, the idea of constraining CNN computation into sparse non-emtpry voxels is first proposed by our O-CNN. Currently, this type of 3D convolution is known as Sparse Convolution in the research community.
Key benefits of ocnn-pytorch
-
Simplicity. The ocnn-pytorch is based on pure PyTorch, it is portable and can be installed with a simple command:
pip install ocnn
. Other sparse convolution frameworks heavily rely on C++ and CUDA, and it is complicated to configure the compiling environment. -
Efficiency. The ocnn-pytorch is very efficient compared with other sparse convolution frameworks. It only takes 18 hours to train the network on ScanNet for 600 epochs with 4 V100 GPUs. For reference, under the same training settings, MinkowskiNet 0.4.3 takes 60 hours and MinkowskiNet 0.5.4 takes 30 hours.
Citation
@article {Wang-2017-ocnn,
title = {{O-CNN}: Octree-based Convolutional Neural Networksfor {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},
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file ocnn-2.2.5.tar.gz
.
File metadata
- Download URL: ocnn-2.2.5.tar.gz
- Upload date:
- Size: 36.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.19
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1f28ffed6aacd3b5c19dd8b8427818f5cbafc0f75e642e8de9674dea9696fc95 |
|
MD5 | 594e976774781e5ca490f5a3e723f7f2 |
|
BLAKE2b-256 | 43ddff07d19a9dd64d64136e61a5560ee9ca5be1133ef3e83c18cd33211a2ded |
File details
Details for the file ocnn-2.2.5-py3-none-any.whl
.
File metadata
- Download URL: ocnn-2.2.5-py3-none-any.whl
- Upload date:
- Size: 53.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.19
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | bdf6ea5a846f78a4622d562f4d8ce91a367ecf7d977c2b24c4a20399c7570289 |
|
MD5 | 9f3ea310f931191247a297f1a886a32e |
|
BLAKE2b-256 | bff36637cdac27fee85e5f8aad78224aac5453bf7aad64cabe07fa1dcc12c693 |