US 12,136,168 B2
Style-controlled generation of visual assets for video games using machine learning
Han Liu, Millbrae, CA (US); Jingwen Liang, Mountain View, CA (US); Jesse Harder, Oakland, CA (US); Gary Ng Thow Hing, Montreal (CA); and Mohsen Sardari, Burlingame, CA (US)
Assigned to Electronic Arts Inc., Redwood City, CA (US)
Filed by Electronic Arts Inc., Redwood City, CA (US)
Filed on Sep. 1, 2021, as Appl. No. 17/463,730.
Prior Publication US 2023/0066897 A1, Mar. 2, 2023
Int. Cl. G06T 7/11 (2017.01); G06N 3/045 (2023.01); G06N 20/00 (2019.01); G06T 7/55 (2017.01); G06T 17/10 (2006.01); G06T 17/20 (2006.01); G06T 19/20 (2011.01)
CPC G06T 17/10 (2013.01) [G06N 3/045 (2023.01); G06N 20/00 (2019.01); G06T 7/11 (2017.01); G06T 7/55 (2017.01); G06T 17/205 (2013.01); G06T 19/20 (2013.01); G06T 2207/20084 (2013.01); G06T 2210/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing system for generating visual assets for video games, the computing system comprising an image segmentation model, a first 3D generation model, and a second 3D generation model, wherein at least one of the first 3D generation model and the second 3D generation model comprises a machine-learning model, and the system is configured to:
obtain: (i) a plurality of images corresponding to the visual asset, each image showing a different view of an object to be generated in the visual asset, and (ii) orientation data for each image that specifies an orientation of the object in the image;
generate, for each image, a segmented image, comprising processing the image using the image segmentation model to segment distinct portions of the image into one or more classes of a predefined set of classes;
generate, for each image, 3D shape data for a portion of the object displayed in the image, comprising inputting the segmented image of the image, the orientation data of the image, and style data for the visual asset to the first 3D generation model, and processing the inputs using the first 3D generation model to generate the 3D shape data for each image; and
generating 3D shape data for the visual asset, comprising processing the generated 3D shape data of each image using the second 3D generation model.