US 12,277,630 B2
Unsupervised style and color cues for transformer-based image generation
Pranav Vineet Aggarwal, Santa Clara, CA (US); Midhun Harikumar, Sunnyvale, CA (US); and Ajinkya Gorakhnath Kale, San Jose, CA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on May 9, 2022, as Appl. No. 17/662,560.
Prior Publication US 2023/0360294 A1, Nov. 9, 2023
Int. Cl. G06T 11/40 (2006.01); G06N 3/045 (2023.01); G06N 3/088 (2023.01); G06T 7/13 (2017.01)
CPC G06T 11/40 (2013.01) [G06N 3/045 (2023.01); G06N 3/088 (2013.01); G06T 7/13 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for image processing, comprising:
identifying target style attributes and target structure attributes for a composite image;
ordering structure feature tokens of a matrix of structure feature tokens to obtain a sequence of structure feature tokens;
combining the sequence of structure feature tokens with target style features to obtain a combined sequence of feature tokens;
generating a matrix of composite feature tokens based on the target style attributes, the target structure attributes, and the combined sequence of feature tokens, wherein the matrix of composite feature tokens comprises a two-dimensional arrangement of composite feature tokens having a plurality of rows and a plurality of columns, and wherein subsequent feature tokens of the matrix of composite feature tokens are autoregressively generated based on previous feature tokens of the matrix of composite feature tokens according to a linear ordering of the matrix of composite feature tokens; and
generating the composite image based on the matrix of composite feature tokens, wherein the composite image includes the target style attributes and the target structure attributes.