Patent US 9,973,773

Patent №

US 9,973,773

Granted

Owner

Lab

AI components

1

vision

Assignment

None on record

Dataset

AIPD

2023_r1 edition

Application

15630393

An image decoding method is provided which includes a time information determination step of determining time information of a current picture, a first reference picture referred to by the current picture and a second reference picture referred to by the current picture; a scaling parameter calculation step of calculating a scaling parameter based on a time distance between the first reference picture and a second reference picture; a weighting coefficient determination step of determining two weighting coefficients based on the scaling parameter; a predictive pixel value generation step of generating a predictive pixel value of the current picture by scaling a pixel value of the first reference picture and a pixel value of the second reference picture using the two weighting coefficients determined in the weighting coefficient determination step; and a decoding step of decoding the current picture using the predictive pixel value.

VisionH04N 19/51H04N 19/105H04N 19/114H04N 19/119H04N 19/172H04N 19/176H04N 19/182H04N 19/31+2 more

AI classification

Vision0.85
AI hardware0.01
Evolutionary computation0.01
Natural language0.00
Machine learning0.00
Knowledge representation0.00
Planning0.00
Speech0.00
© 2026 NYSGPT2525 LLC