GENERATING OUTPUT PIXELS OF AN OUTPUT IMAGE FROM ONE OR MORE INPUT IMAGES USING A SET OF MOTION VECTORS HAVING A SUB-PIXEL ACCURACY

Patent №

US 8,068,682

Granted

2011-11-29

Filed 2007

Owner

SONY UNITED KINGDOM LIMITED

Lab

AI components

1

vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

11909810

An image processing apparatus in which output pixels of an output image are generated from one or more input images using motion vectors having a sub-pixel accuracy. A motion vector allocator allocates motion vectors in the pixels, and compares a current output pixel with test image areas pointed to by motion vectors in the pixels to detect a most suitable motion vector for the current output pixel. A pixel generator operates in a first mode if the output pixel is within a threshold displacement from an image region having substantially different motion characteristics to those of that output pixel, and in a second mode otherwise. The pixel generator includes a spatial filter generating an output pixel value at a required pixel position to a sub-pixel accuracy.

VisionH04N 5/144H04N 7/012

AI classification

Vision1.00
AI hardware0.01
Planning0.00
Knowledge representation0.00
Speech0.00
Natural language0.00
Evolutionary computation0.00
Machine learning0.00

Ownership

SONY UNITED KINGDOM LIMITED

assignment · 198870902

Assignors

LIVING, JONATHAN

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC