Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Octree-based 3D Convolutional Neural Networks [SIGGRAPH 2017]
| Date | Stars |
|---|---|
| 2026-07-31 | 252 |
| 2026-08-06 | 252 |
| 2026-08-07 | 252 |
| 2026-08-13 | 253 |
| 2026-08-14 | 253 |
| 2026-08-15 | 253 |
| 2026-08-18 | 253 |
| 2026-09-02 | 255 |
| 2026-09-21 | 256 |
| 2026-09-26 | 257 |
| 2026-10-30 | 258 |
| 2026-11-04 | 258 |
Today
— stars today
This week
+1 stars this week
This month
+1 stars this month
Momentum
0.0
growth rate 0.39%/day
# O-CNN **[Documentation](https://ocnn-pytorch.readthedocs.io)** [](https://ocnn-pytorch.readthedocs.io/en/latest/?badge=latest) [](https://pepy.tech/project/ocnn) [](https://pepy.tech/project/ocnn) [](https://pypi.org/project/ocnn/) This repository contains the **pure PyTorch**-based implementation of [O-CNN](https://wang-ps.github.io/O-CNN.html). The code is compatible with `Pytorch>=1.6.0`, while **`Pytorch>=2.8.0` is required for Triton-based convolutions**. The *original* implementation of O-CNN is based on C++ and CUDA and can be found [here](https://github.com/Microsoft/O-CNN), which has received [](https://github.com/microsoft/O-CNN) and [](https://github.com/microsoft/O-CNN). O-CNN is an octree-based 3D convolutional neural network framework for 3D data. 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. Currently, this type of 3D convolution is known as Sparse Convolution in the research community. The concept of Sparse Convolution in O-CNN is the same with [SparseConvNet](https://openaccess.thecvf.com/content_cvpr_2018/papers/Graham_3D_Semantic_Segmentation_CVPR_2018_paper.pdf), [MinkowskiNet](https://github.com/NVIDIA/MinkowskiEngine), and [SpConv](https://github.com/traveller59/spconv). The key difference is that our O-CNN uses `octrees` to index the sparse voxels, while these works use `Hash Tables`. However, I believe that `octrees` may be the right choice for Sparse Convolution. With `octrees`, I can implement the Sparse Convolution with pure PyTorch. More importantly, with `octrees`, I can also build efficient transformers for 3D data -- [OctFormer](https://github.com/octree-nn/octformer), which is extremely hard with `Hash Tables`. Our O-CNN is published in SIGGRAPH 2017, 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. 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, i.e. Sparse Convolution, is first proposed by our O-CNN**. <!-- The camera-ready version of our O-CNN was submitted to SIGGRAPH in April, 2018. --> <!-- Developed in collaboration with authors from [PointCNN](https://arxiv.org/abs/1801.07791), [Dr. Yangyan Li](https://yangyan.li/) and [Prof. Baoquan Chen](https://baoquanchen.info/), --> This library supports point cloud processing from the ground up. The library provides essential components for converting raw point clouds into octrees to perform convolution operations. Of course, it also supports other 3D data formats, such as meshes and volumetric grids, which can be converted into octrees to leverage the library's capabilities. ## Updates - **2026.08.05**: Release `v2.3.3`, this release mainly adds specialized octree convolutions, flexible start_depth construction, a ShapeNet normal-estimation workflow. - **2026.05.07**: Release `v2.3.2`, this release focuses on stability, performance, and usability improvements. - **2026.02.08**: Release `v2.3.1`, improving the interfaces of octree convolutions and simplifying the triton kernels. - **2026.02.02**: Release `v2.3.0`, incorporating Triton to accelerate octree-based sparse convolution, resulting in a performance boost of up to **2.5 times faster than the latest spconv**! - **2025.12.18**: Release `v2.2.8`, improving neighbor search efficiency.
Excerpt of 4,962 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f874bbffe4f0303b, llm:Description: 'Octree-based 3D Convolutional Neural Networks [SIGGRAPH 2017]'. Repository name and topic indicate octree neural network for 3D convnets (PyTorch).
matched fp:f874bbffe4f0303b, llm:Description: 'Octree-based 3D Convolutional Neural Networks [SIGGRAPH 2017]'. Repository name and topic indicate octree neural network for 3D convnets (PyTorch).
matched fp:f874bbffe4f0303b, llm:Description: 'Octree-based 3D Convolutional Neural Networks [SIGGRAPH 2017]'. Repository name and topic indicate octree neural network for 3D convnets (PyTorch).