US 12,118,669 B2
Subdividing a three-dimensional mesh utilizing a neural network
Vladimir Kim, Seattle, WA (US); Siddhartha Chaudhuri, Bangalore (IN); Noam Aigerman, San Francisco, CA (US); Hsueh-ti Liu, Toronto (CA); and Alec Jacobson, Toronto (CA)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Aug. 23, 2022, as Appl. No. 17/821,704.
Application 17/821,704 is a continuation of application No. 16/863,189, filed on Apr. 30, 2020, granted, now 11,423,617.
Prior Publication US 2023/0267686 A1, Aug. 24, 2023
Int. Cl. G06T 17/20 (2006.01); G06N 3/02 (2006.01); G06N 3/08 (2023.01); G06T 7/13 (2017.01)
CPC G06T 17/20 (2013.01) [G06N 3/02 (2013.01); G06N 3/08 (2013.01); G06T 7/13 (2017.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
determining local geometries comprising adjacent vertices of existing vertices in a three-dimensional mesh;
generating, utilizing at least one neural network, a set of displacement coordinates displacing a subset of the existing vertices from initial positions of the subset of the existing vertices in the three-dimensional mesh to new positions and a set of new coordinates for new vertices along edges connecting the existing vertices by causing the at least one neural network to generate the set of displacement coordinates and the set of new coordinates from feature vectors of the local geometries;
generating a subdivided three-dimensional mesh comprising vertices at positions according to the set of displacement coordinates for the existing vertices and the set of new coordinates for the new vertices along the edges connecting the existing vertices; and
recursively subdividing the three-dimensional mesh to generate a plurality of levels of subdivided three-dimensional meshes according to the set of displacement coordinates for the existing vertices and the set of new coordinates for the new vertices generated utilizing the at least one neural network.