Git Product home page Git Product logo

euler_vid_mag's Introduction

euler_vid_mag

A python implementation MIT's Eulerian Video Magnification algorithms from both the Siggraph 2012 paper (Hao-Yu Wu, Michael Rubinstein, Eugene Shih, John Guttag, Frédo Durand and William T. Freeman) and also the "new-and-improved" phase-based approach from the 2013 paper (Neal Wadhwa, Michael Rubinstein, Frédo Durand and William T. Freeman). The code presented here is a python implementation of the matlab sources provided by MIT, which are used under license with all credit going to the authors of these algorithms; additionally, the linear implementation leans heavily on https://github.com/LabForComputationalVision/pyrtools for generating Laplacian pyramids.

The original papers can be found here (along with more recent developments) http://people.csail.mit.edu/mrub/vidmag/ and they make for an excellent read.

Installation: Installing into a virtualenv is recommended. At the command prompt, enter:

pip install -e .

To reproduce the results for the Siggraph 2013 paper:

  1. Download the source videos (1.3GB) from the project web page into a directory called sample.
  2. Type reproduce_results_siggraph13 to reproduce the results in the paper.

There is also a little tkinter UI for demo purposes, which can be launched from the shell like this:

phase_amplify_app

The gifs below are the MIT file 'car_engine.avi' before & after processing with the phase-based algorithm:

screenshot screenshot

Note that OpenCV 4.x is required (should be compatible with 3.x versions too).

euler_vid_mag's People

Contributors

aloyisus avatar

Stargazers

 avatar jac young avatar  avatar  avatar  avatar  avatar Pertti Palo avatar  avatar Hamza Sultansarip avatar Gustavo Alves avatar Liam Gray avatar  avatar  avatar  avatar wangyunlu avatar Esteban Ponce de Leon avatar Shavell avatar Josh Teneycke avatar  avatar  avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.