US 11,983,394 B2
System and method for generating photorealistic synthetic images based on semantic information
Raja Bala, Pittsford, NY (US); Sricharan Kallur Palli Kumar, Mountain View, CA (US); and Matthew A. Shreve, Campbell, CA (US)
Assigned to Xerox Corporation, Norwalk, CT (US)
Filed by Palo Alto Research Center Incorporated, Palo Alto, CA (US)
Filed on Nov. 23, 2022, as Appl. No. 17/993,708.
Application 17/993,708 is a continuation of application No. 16/040,220, filed on Jul. 19, 2018, granted, now 11,537,277.
Prior Publication US 2023/0090801 A1, Mar. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/04845 (2022.01); G06F 3/04847 (2022.01); G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2023.01); G06N 3/088 (2023.01); G06T 5/00 (2006.01); G06T 7/11 (2017.01); G06T 7/143 (2017.01); G06T 7/35 (2017.01); G06T 11/00 (2006.01)
CPC G06F 3/04845 (2013.01) [G06F 3/04847 (2013.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/088 (2013.01); G06T 5/002 (2013.01); G06T 7/11 (2017.01); G06T 7/143 (2017.01); G06T 7/35 (2017.01); G06T 11/00 (2013.01); G06T 2207/20016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating semantically accurate synthetic images, comprising:
generating a first synthetic image using a first artificial intelligence (AI) model;
presenting the first synthetic image in a user interface, wherein the user interface is configured to receive information indicating image units of the first synthetic image that are semantically irregular;
obtaining semantic information for the semantically irregular image units from a user via the user interface;
incorporating the semantic information into a second AI model; and
generating a second synthetic image using the second AI model, wherein the second synthetic image is generated when a metric is within a threshold and includes one or more improved image units compared to the first synthetic image.