https://github.com/pathak22/pyflow

Fast, accurate and easy to run dense optical flow with python wrapper
https://github.com/pathak22/pyflow

computer-vision dense-flow image-processing optical-flow python-optical-flow

Last synced: 2 days ago
JSON representation

Fast, accurate and easy to run dense optical flow with python wrapper

• Host: GitHub
• URL: https://github.com/pathak22/pyflow
• Owner: pathak22
• License: other
• Created: 2016-07-16T04:50:01.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2019-05-31T17:38:55.000Z (over 5 years ago)
• Last Synced: 2024-12-28T23:48:49.474Z (9 days ago)
• Topics: computer-vision, dense-flow, image-processing, optical-flow, python-optical-flow
• Language: C++
• Homepage:
• Size: 878 KB
• Stars: 653
• Watchers: 17
• Forks: 139
• Open Issues: 21
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
## Python Dense Optical Flow

**Python** wrapper for Ce Liu's [C++ implementation](https://people.csail.mit.edu/celiu/OpticalFlow/) of Coarse2Fine Optical Flow. This is **super fast and accurate** optical flow method based on Coarse2Fine warping method from Thomas Brox. This python wrapper has minimal dependencies, and it also eliminates the need for C++ OpenCV library. For real time performance, one can additionally resize the images to a smaller size.

Run the following steps to download, install and demo the library:

  ```Shell

  git clone https://github.com/pathak22/pyflow.git

  cd pyflow/

  python setup.py build_ext -i

  python demo.py    # -viz option to visualize output

  ```

This wrapper code was developed as part of our [CVPR 2017 paper on Unsupervised Learning using unlabeled videos](http://cs.berkeley.edu/~pathak/unsupervised_video/). Github repository for our CVPR 17 paper is [here](https://github.com/pathak22/unsupervised-video).