US Patent Application 18188908. DERIVATION OF AFFINE MERGE CANDIDATES WITH LINEAR REGRESSION FOR VIDEO CODING simplified abstract
Contents
DERIVATION OF AFFINE MERGE CANDIDATES WITH LINEAR REGRESSION FOR VIDEO CODING
Inventors
Yan Zhang of San Diego CA (US)
Han Huang of San Diego CA (US)
Vadim Seregin of San Diego CA (US)
Muhammed Zeyd Coban of Carlsbad CA (US)
Marta Karczewicz of San Diego CA (US)
DERIVATION OF AFFINE MERGE CANDIDATES WITH LINEAR REGRESSION FOR VIDEO CODING - A simplified explanation of the abstract
- This abstract for appeared for patent application number 18188908 Titled 'DERIVATION OF AFFINE MERGE CANDIDATES WITH LINEAR REGRESSION FOR VIDEO CODING'
Simplified Explanation
The abstract describes a method for encoding a block of video data using an affine mode. This method involves determining a refined affine model for the block by using a linear regression process with a base motion vector field and a guidance motion vector field as inputs. The method also includes determining affine merge candidates for the block based on the refined affine model. Finally, the block of video data is coded using the affine merge candidates.
Original Abstract Submitted
A method for coding a block of video data using affine mode includes determining a refined affine model for the current block of video data from a linear regression process using a base motion vector field and a guidance motion vector field as inputs to the linear regression process. The method further includes determining affine merge candidates for the current block using the refined affine model, and coding the current block of video data using the affine merge candidates.
