18502868. MODEL FINE-TUNING FOR AUTOMATED AUGMENTED REALITY DESCRIPTIONS (Snap Inc.)
MODEL FINE-TUNING FOR AUTOMATED AUGMENTED REALITY DESCRIPTIONS
Organization Name
Inventor(s)
Maksim Gusarov of Santa Monica CA US
Kwot Sin Lee of Weehawken NJ US
Patrick Poirson of Gilbert AZ US
MODEL FINE-TUNING FOR AUTOMATED AUGMENTED REALITY DESCRIPTIONS
This abstract first appeared for US patent application 18502868 titled 'MODEL FINE-TUNING FOR AUTOMATED AUGMENTED REALITY DESCRIPTIONS
Original Abstract Submitted
A second input image is generated by applying a target augmented reality (AR) effect to a first input image. The first input image and the second input image are provided to a first visual-semantic machine learning model to obtain output describing at least one feature of the target AR effect. The first visual-semantic machine learning model is fine-tuned from a second visual-semantic machine learning model by using training samples. Each training sample comprises a first training image, a second training image, and a training description of a given AR effect. The second training image is generated by applying the given AR effect to the first training image. A description of the target AR effect is selected based on the output of the visual-semantic machine learning model. The description of the target AR effect is stored in association with an identifier of the target AR effect.
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
