US 12,437,505 B2
Generating templates using structure-based matching
Vlad-Constantin Lungu-Stan, Buzau (RO); Ionuţ Mironică, Bucharest (RO); Oliver Brdiczka, San Jose, CA (US); and Alexandru Vasile Costin, Monte Sereno, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Oct. 13, 2022, as Appl. No. 17/965,291.
Prior Publication US 2024/0127577 A1, Apr. 18, 2024
Int. Cl. G06V 10/00 (2022.01); G06T 11/60 (2006.01); G06V 10/74 (2022.01)
CPC G06V 10/761 (2022.01) [G06T 11/60 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a computing device, input data describing a set of digital design elements;
representing, by the computing device, the input data as a sentence in a design structure language that describes structural relationships between design elements included in the set of digital design elements;
generating, by the computing device, an input template embedding by a machine learning model based on the sentence in the design structure language, the machine learning model trained to receive sentences in the design structure language as inputs and generate embeddings in a latent space for the sentences in the design structure language as outputs; and
generating, by the computing device, a digital template that includes the set of digital design elements for display in a user interface based on the input template embedding.