/Patent Tracker
SamsungGranted patentAI & softwareInterest 4/10

Samsung patents method to sharpen 3D graphics using motion data

Patent drawing
Patent drawing from the official filing.

This patent describes a technique for creating sharper 3D images by combining a low-resolution render with data from previous frames. It uses motion tracking to align past images and adjusts pixel positions to fill in details, resulting in a clearer final picture.

Why it mattersThis could improve the visual quality of virtual reality or gaming displays by making images look smoother and more detailed without requiring higher hardware power.

In the filing’s own words

A supersampling method includes generating a current rendered image frame by performing jittered sampling on a three-dimensional (3D) scene, based on sub-pixels of low-resolution pixels for the current rendered image frame; generating a current warped image frame by warping a previous output image frame, based on a motion vector map corresponding to a difference between the current rendered image frame and a previous rendered image frame; generating a current shifted image frame by shifting pixels of the current warped image frame, based on a change in sampling positions based on the jittered sampling; and generating a current output image frame, based on the current rendered image frame and the current shifted image frame.

What exactly they claim (claim 1)

1. A supersampling method, comprising: generating a current rendered image frame by performing jittered sampling on a three-dimensional (3D) scene, based on sub-pixels of low-resolution pixels for the current rendered image frame; generating a current warped image frame by warping a previous output image frame, based on a motion vector map corresponding to a difference between the current rendered image frame and a previous rendered image frame; generating a current shifted image frame by shifting pixels of the current warped image frame, based on a change in sampling positions based on the jittered sampling; and generating a current output image frame, based on the current rendered image frame and the current shifted image frame; selecting target pixels in the current shifted image frame based on the sampling positions of the jittered sampling; and replacing the target pixels with pixels of the current rendered image frame.

Facts

Company
Samsung (SAMSUNG ELECTRONICS CO., LTD.)
Official title
Neural supersampling method and device
Patent number
US12755334B2
Application number
18404438
Filed
Jan 4, 2024
Granted
Oct 6, 2026
Inventors
6
Claims
19

Classified under

G06T 3/40 Physics & computingG06T 3/18 Physics & computingG06T 5/50 Physics & computingG06T 7/20 Physics & computingG06T 15/00 Physics & computingG06T 2207/20221 Physics & computing

More from Samsung in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.