This is the public page of AI-Enhanced Video Coding (MPAI-EVC) standard. See the MPAI-EVC homepage.

MPAI-EVC is an MPAI project for a video compression standard that substantially en­hances the performance of a traditional video codec (MPEG-5 EVC in this case) by improving or replacing traditional tools with AI-based tools.

 

Reference schema with tools currently under development in MPAI-EVC (in red rectangles).

MPAI is currently engaged in the MPAI-EVC Evidence Project seeking to demonstrate that extending or replacing tools can offer at least 25% performance improvement.

MPAI-EVC has already developed the Use Cases and Functional Requirements and currently is actively engaged in refining enhanced intra prediction (exploitation of redundancies within the same image), in-loop filter, (enhancement of the reconstructed image) and super resolution (spatial upscaling) techniques.

If you wish to participate in this work you have the following options

  1. Join MPAI
  2. Participate until the MPAI-EVC Functional Requirements are approved (after that only MPAI members can participate) by sending an email to the MPAI Secretariat.
  3. Keep an eye on this page.

Return to the MPAI-EVC page