US 11,836,844 B2
Motion vector optimization for multiple refractive and reflective interfaces
Pawel Kozlowski, Truckee, CA (US); and Maksim Aizenshtein, Sammamish, WA (US)
Assigned to Nvidia Corporation, Santa Clara, CA (US)
Filed by Nvidia Corporation, Santa Clara, CA (US)
Filed on Mar. 3, 2022, as Appl. No. 17/686,081.
Prior Publication US 2023/0281906 A1, Sep. 7, 2023
Int. Cl. G06T 15/00 (2011.01); G06T 5/00 (2006.01); G06T 7/70 (2017.01); G06T 7/20 (2017.01)
CPC G06T 15/00 (2013.01) [G06T 5/002 (2013.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving image data for a first image frame and a second image frame;
locating, based at least in part on the image data, at least one surface point in common between the first image frame and the second image frame;
determining a background region, corresponding to a background depicted using the first image frame, based at least in part on the at least one common surface point and one or more vertices corresponding to at least one beam path visible through one or more layers of refractive interfaces depicted using the first image frame;
determining a pixel of interest in the background region; and
generating, based at least in part on at least one of a cross function or an optimization function, at least one motion vector representing an offset of the pixel of interest between the first image frame and the second image frame.