US 11,776,095 B2
Photo relighting using deep neural networks and confidence learning
Tiancheng Sun, Mountain View, CA (US); Yun-ta Tsai, Mountain View, CA (US); and Jonathan Barron, Mountain View, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 17/260,364
Filed by GOOGLE LLC, Mountain View, CA (US)
PCT Filed Apr. 1, 2019, PCT No. PCT/US2019/025205
§ 371(c)(1), (2) Date Jan. 14, 2021,
PCT Pub. No. WO2020/068158, PCT Pub. Date Apr. 2, 2020.
Claims priority of provisional application 62/749,081, filed on Oct. 22, 2018.
Claims priority of provisional application 62/735,506, filed on Sep. 24, 2018.
Prior Publication US 2021/0264576 A1, Aug. 26, 2021
Int. Cl. G06T 5/00 (2006.01); G06T 15/50 (2011.01)
CPC G06T 5/008 (2013.01) [G06T 15/506 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
training a neural network to apply a lighting model to an input image utilizing confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image, wherein the light predictions comprise a prediction of an original light model indicative of a location of one or more environmental light sources with reference to an object in the input image;
receiving a particular input image of a particular object and data about a particular lighting model to be applied to the particular input image at a computing device; and
determining, by the computing device and based on a particular original light model predicted by the neural network, an output image of the particular object by using the trained neural network to apply the particular lighting model to the particular input image of the particular object.