US 12,190,428 B2
Deep relightable appearance models for animatable face avatars
Jason Saragih, Pittsburgh, PA (US); Stephen Anthony Lombardi, Pittsburgh, PA (US); Shunsuke Saito, Pittsburgh, PA (US); Tomas Simon Kreuz, Pittsburgh, PA (US); Shih-En Wei, Pittsburgh, PA (US); Kevyn Alex Anthony McPhail, Pittsburgh, PA (US); Yaser Sheikh, Pittsburgh, PA (US); and Sai Bi, La Jolla, CA (US)
Assigned to Meta Platforms Technologies, LLC, Menlo Park, CA (US)
Filed by Meta Platforms Technologies, LLC, Menlo Park, CA (US)
Filed on Jun. 13, 2023, as Appl. No. 18/333,647.
Application 18/333,647 is a continuation of application No. 17/580,486, filed on Jan. 20, 2022, granted, now 11,715,248.
Claims priority of provisional application 63/141,871, filed on Jan. 26, 2021.
Prior Publication US 2023/0326112 A1, Oct. 12, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 13/40 (2011.01); G06T 11/00 (2006.01); G06T 15/04 (2011.01); G06T 15/50 (2011.01); G06T 15/60 (2006.01)
CPC G06T 13/40 (2013.01) [G06T 11/001 (2013.01); G06T 15/04 (2013.01); G06T 15/506 (2013.01); G06T 15/60 (2013.01); G06T 2215/12 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
generating texture maps for a subject, based on multiple images including multiple views of the subject under a plurality of lighting conditions, the texture maps including spatially varied expressions and viewpoints across the plurality of lighting conditions;
generating a final texture map based on the texture maps and intensity-defined weights corresponding to the plurality of lighting conditions;
generating, based on the final texture map, a view of the subject illuminated by a light source selected from an environment of the subject; and
providing the view of the subject to an immersive reality application running in a client device.