US 12,293,466 B2
Systems and methods for generating a model database with blendshape representation
Igor Borovikov, Foster City, CA (US); David Auclair, Orlando, FL (US); Mihai Anghelescu, Coquitlam (CA); and Harold Chaput, Belmont, CA (US)
Assigned to Electronic Arts Inc., Redwood City, CA (US)
Filed by Electronic Arts Inc., Redwood City, CA (US)
Filed on Mar. 24, 2023, as Appl. No. 18/125,933.
Prior Publication US 2024/0320920 A1, Sep. 26, 2024
Int. Cl. G06T 17/20 (2006.01)
CPC G06T 17/205 (2013.01) 17 Claims
OG exemplary drawing
 
1. A method for generating a master representation of input models, the method comprising:
receiving, by one or more processors, a first base mesh, wherein the first base mesh is a polygonal mesh having a first topology, wherein the first base mesh is associated with a first set of blendshapes to deform the first base mesh;
receiving, by the one or more processors, a second base mesh, wherein the second base mesh is a polygonal mesh having a second topology, wherein the second base mesh is associated with a second set of blendshapes to deform the second base mesh, wherein the second topology is different from the first topology;
combining, by the one or more processors, the first topology of the first base mesh and the second topology of the second base mesh into a combined mesh topology representation;
combining, by the one or more processors, the first set of blendshapes and the second set of blendshapes into a combined blendshape representation, wherein combining the first set of blendshapes and the second set of blendshapes into the combined blendshape representation comprises generating a blendshape basis for the combined blendshape representation that minimizes a discretization loss represented in the blendshape basis over a set of target mesh topologies, wherein the set of target mesh topologies includes the first topology and the second topology; and
outputting, by the one or more processors, the combined mesh topology representation and the combined blendshape representation as a master representation, wherein the master representation can be queried with a target topology and associated blendshape vector.