<-Foreword      Go to ToC       Scope ->

(Informative)

Many applications require video filtering, for instance in video compression where the full data rate reduction process involves capture, down-sampling, encoding, transport, decoding, up-sampling, and rendering.

Typical up-sampling technologies used in video coding applications Bi-cubic and Lanczos filters. However, they have a major limitations because they perform purely mathematical operations on the decoded video sequence.

Up-sampling filters resulting from a process of training using a large number of video sequences are highly non-linear and are able to reproduce  the original-resolution video sequences beyond the simple interpolation of pixels in the sub-sampled video frames.

Technical Specification: AI-Enhanced Video Coding (MPAI-EVC) – Up-sampling Filter for Video applications (EVC-UFV) V1.0 specifies procedures to design up-sampling filter for video applications based on Super Resolution and to reduce their complexity..

 

<-Foreword      Go to ToC       Scope ->