Deformable Surface Tracking and Alpha Matting for the Automation of Post-production Workflows

The AutoPost plugins (http://autopost-project.eu) aim to automate major parts of the daily workload in audio-visual post-production, particularly for small and medium post houses and, with it, to make post-production more efficient by reducing time-consuming and costly manual processing. To ensure industry adoption, the algorithms are integrated into OpenFX for multi-platform post-production targeting regular 2D and 3D productions, Visual effects and 2D-to-3D conversion.

Highlights:

  • SDKs and plugins that bridge the gap between state-of-the-art computer vision algorithms and commercial tools
  • Ready-to-market tracking and matting plugins for established post-production platforms
  • Solutions targeting small and medium post-production companies for reducing their overall production costs and boosting their competitiveness in the global market
  • Avoid expensive green screen, motion capture or rotomation techniques
  • User-centered research for post-production

 

Applications

  • Object and skin manipulation
  • Appearance modification: digital makeup, ageing and de-ageing
  • Scene extension and replacement
  • Compositing and matting hair with arbitrary and natural backgrounds •
  • Object selection for color grading and finishing

Deformable Surface Tracking

Deformable tracking methods that estimate temporally consistent surface motion, deformation, and shading changes, even in presence of temporary occlusions under real-world conditions.

 

Natural Video Matting

Matting methods that provide accurate and more realistic mattes for VFX and post-production processes with particular attention to motion blur and deformable surfaces under real-world conditions.

Demonstration

You can now enjoy in our Vimeo channel (https://vimeo.com/autopost) the videos showed during NAB2016 demonstrating the AutoPost surface tracking and natural matting plugins.

 


Download
Download our flyer
flyer_autopost.pdf
Adobe Acrobat Document 1.2 MB

AutoPost project was co-funded by the European Commission under the Horizon 2020 Programme