Systems and methods for synthetic image generation

An image generation method for unsupervised cross-domain image generation relative to a first image domain and a second image domain, the image generation method comprising:

• receiving a 3D CAD (computer aided design) model comprising 3D model images of a target object;
• based on the 3D CAD model of the target object, generating a plurality of augmented CAD models of the target object comprising a plurality of data sets, each data set respectively corresponding to an associated one of a plurality of attribute classes, each data set comprising a plurality of 2D model images;
• inputting the plurality of data sets into a generative adversarial network comprising a plurality of generators respectively corresponding to the plurality of attribute classes and a plurality of discriminators respectively corresponding to the plurality of generators;
• generating synthetic photorealistic images of the target object using the plurality of generators, the synthetic photorealistic images including attributes in accordance with the plurality of data sets corresponding to the plurality of attribute classes;
• and
• outputting the synthetic photorealistic images of the target object, wherein
• the plurality of attribute classes includes an anomaly class;
• and
• the plurality of augmented CAD models are generated by adding various anomalies into the 3D CAD model augmented in accordance with anomaly instructions.

An image generation system for unsupervised cross-domain image generation relative to a first image domain and a second image domain, the image generation system comprising:

• a processor, and a memory storing instructions that, when executed by the processor, cause the system to:
• receive a 3D CAD (computer aided design) model comprising 3D model images of a target object;
• based on the 3D CAD model of the target object, generate a plurality of augmented CAD models of the target object comprising a plurality of data sets, each data set respectively corresponding to an associated one of a plurality of attribute classes, each data set comprising a plurality of 2D model images;
• input the plurality of data sets into a generative adversarial network comprising a plurality of generators respectively corresponding to the plurality of attribute classes and a plurality of discriminators respectively corresponding to the plurality of generators;
• generate synthetic photorealistic images of the target object using the plurality of generators, the synthetic photorealistic images including attributes in accordance with the plurality of data sets corresponding to the plurality of attribute classes;
• and
• inputting the synthetic photorealistic images of the target object into an anomaly detection artificial intelligence model to train the anomaly detection artificial intelligence model to detect anomalies on the target object, wherein
• one of the attribute classes is an anomaly class;
• one of the plurality of generators is an anomaly class generator including:
• a first image generator configured to generate synthetic images having a similar appearance to one or more of the photorealistic images in the second image domain while including a semantic content of one or more 2D model images depicting anomalies in the first image domain in accordance with an anomaly class data set in the augmented CAD models of the target object;
• a second image generator configured to generate synthetic images having a similar appearance to one or more of the 2D model images depicting anomalies in the first image domain while including semantic content of one or more photorealistic images in the second image domain;
• the discriminator is an anomaly class discriminator including:
• a first image discriminator configured to discriminate real photorealistic images in the second image domain against synthetic photorealistic images generated by the first image generator;
• and
• a second image discriminator configured to discriminate real 2D model images depicting anomalies in the first image domain against synthetic 2D model images depicting anomalies generated by the second image generator, wherein
• the plurality of augmented CAD models are generated by:
• adding various anomalies into the 3D CAD model augmented in accordance with anomaly instructions;
• and
• rendering 2D model images of an anomaly class data set of the anomaly class using the augmented 3D CAD model.