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.
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
| Date | Stars |
|---|---|
| 2026-07-24 | 906 |
| 2026-07-25 | 906 |
| 2026-07-28 | 906 |
| 2026-07-30 | 906 |
| 2026-08-06 | 906 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 3DMatch Toolbox
3DMatch is a ConvNet-based local geometric feature descriptor that operates on 3D data (i.e. point clouds, depth maps, meshes, etc.). This toolbox provides code to use 3DMatch for geometric registration and keypoint matching, as well as code to train 3DMatch from existing RGB-D reconstructions. This is the reference implementation of our paper:
### 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
[PDF](https://arxiv.org/pdf/1603.08182.pdf) | [Webpage & Benchmarks & Datasets](http://3dmatch.cs.princeton.edu/) | [Video](https://www.youtube.com/watch?v=gZrsJJtDvvA)
*[Andy Zeng](http://andyzeng.com/), [Shuran Song](http://3dvision.princeton.edu/people/shurans/), [Matthias Nießner](http://www.niessnerlab.org/members/matthias_niessner/profile.html), [Matthew Fisher](https://research.adobe.com/person/matt-fisher/), [Jianxiong Xiao](http://3dvision.princeton.edu/people/xj/), and [Thomas Funkhouser](http://www.cs.princeton.edu/~funk/)*
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 **[Oral Presentation](https://www.youtube.com/watch?v=qNVZl7bCjsU&list=PL_bDvITUYucADb15njRd7geem8vxOyo6N&index=3)**
Matching local geometric features on real-world depth images is a challenging task due to the noisy, low-resolution, and incomplete nature of 3D scan data. These difficulties limit the performance of current state-of-art methods, which are typically based on histograms over geometric properties. In this paper, we present 3DMatch, a data-driven model that learns a local volumetric patch descriptor for establishing correspondences between partial 3D data. To amass training data for our model, we propose an unsupervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions. Experiments show that our descriptor is not only able to match local geometry in new scenes for reconstruction, but also generalize to different tasks and spatial scales (e.g. instance-level object model alignment for the Amazon Picking Challenge, and mesh surface correspondence). Results show that 3DMatch consistently outperforms other state-of-the-art approaches by a significant margin.
#### Citing
If you find this code useful in your work, please consider citing:
```shell
@inproceedings{zeng20163dmatch,
title={3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions},
author={Zeng, Andy and Song, Shuran and Nie{\ss}ner, Matthias and Fisher, Matthew and Xiao, Jianxiong and Funkhouser, Thomas},
booktitle={CVPR},
year={2017}
}
```
#### License
This code is released under the Simplified BSD License (refer to the LICENSE file for details).
#### Benchmarks and Datasets
All relevant information and downloads can be found [here](http://3dmatch.cs.princeton.edu/).
#### Contact
If you have any questions or find any bugs, please let me know: [Andy Zeng](http://www.cs.princeton.edu/~andyz/) andyz[at]princeton[dot]edu
## Change Log
* **Mar. 20, 2018.** Update: added labels for test-set of keypoint matching benchmark (for convenience).
* **Nov. 02, 2017.** Bug fix: added `#include <random>` to utils.hpp in demo code.
* **Oct. 30, 2017.** Bug fix: included Quoc-Huy's fix for NaN errors that occasionally occur during training.
* **Oct. 28, 2017.** Notice: demo code only reads 3D point clouds saved in a simple binary format. If you would like to run the 3DMatch demo code on your own point cloud format, please modify demo.cu accordingly.
* **Apr. 06, 2017.** Notice: 3DMatch uses cuDNN 5.1. Revised install instructions.
## Dependencies
Our reference implementation of 3DMatch, as well as other components in this toolbox, require the following dependencies. Tested on Ubuntu 14.04.
0. [CUDA 7.5](https://developer.nvidia.com/cuda-toolkit-archive) and [cuDNN 5.1](https://developer.nvidia.com/cudnn). You may need to register with NVIDIA. Below are some additional steps to set up cuDNN 5.1. **NOTExcerpt of 16,670 characters
Read on GitHub
55
13
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6822415ca21d7fcd, topic:computer-vision, readme:computer vision
matched fp:6822415ca21d7fcd, topic:deep-learning