US 12,169,914 B2
Temporal techniques of denoising Monte Carlo renderings using neural networks
Thijs Vogels, Lausanne (CH); Fabrice Rousselle, Ostermundingen (CH); Jan Novak, Meilen (CH); Brian McWilliams, Zürich (CH); Mark Meyer, San Francisco, CA (US); and Alex Harvill, Berkeley, CA (US)
Assigned to PIXAR, Emeryville, CA (US); and DISNEY ENTERPRISES, INC., Burbank, CA (US)
Filed by Pixar, Emeryville, CA (US); and Disney Enterprises, Inc., Burbank, CA (US)
Filed on Nov. 9, 2022, as Appl. No. 17/984,132.
Application 17/984,132 is a continuation of application No. 16/050,314, filed on Jul. 31, 2018, granted, now 11,532,073.
Claims priority of provisional application 62/650,106, filed on Mar. 29, 2018.
Prior Publication US 2023/0083929 A1, Mar. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 5/70 (2024.01); G06F 17/18 (2006.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 5/04 (2023.01); G06N 5/046 (2023.01); G06N 20/00 (2019.01); G06T 5/50 (2006.01); G06T 15/06 (2011.01); G06T 15/50 (2011.01)
CPC G06T 5/70 (2024.01) [G06F 17/18 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 5/046 (2013.01); G06N 20/00 (2019.01); G06T 5/50 (2013.01); G06T 15/06 (2013.01); G06T 15/506 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of denoising images rendered by path tracing, the method comprising:
receiving a sequence of frames rendered by path tracing, the sequence of frames including a first frame and one or more temporal neighboring frames;
receiving a reference image corresponding to the first frame;
extracting, using one or more first neural networks, sets of first features from the sequence of frames;
storing a second neural network including a plurality of layers and a plurality of nodes, the second neural network configured to:
extract a set of temporal features from the sets of first features; and
training the second neural network to obtain a plurality of optimized parameters associated with the plurality of nodes of the second neural network using the sequence of frames and the reference image corresponding to the first frame.