Generating a digital image using a generative adversarial network
AssigneeeBay Inc.
InventorsMohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
Life of this patent
Estimating the term…
Loading patent…
AssigneeeBay Inc.
InventorsMohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
Estimating the term…
Various embodiments described herein utilize multiple levels of generative adversarial networks (GANs) to facilitate generation of digital images based on user-provided images. Some embodiments comprise a first generative adversarial network (GAN) and a second GAN coupled to the first GAN, where the first GAN includes an image generator and at least two discriminators, and the second GAN includes an image generator and at least one discriminator. According to some embodiments, the (first) image generator of the first GAN is trained by processing a user-provided image using the first GAN. For some embodiments, the user-provided image and the first generated image, generated by processing the user-provided image using the first GAN, are combined to produce a combined image. For some embodiments, the (second) image generator of the second GAN is trained by processing the combined image using the second GAN.
(canceled)
A system comprising:
A method for generating an item listing according to a user-provided image, the method comprising:
A method for generating an item listing according to a user-provided image, the method comprising:
Dependencies are inferred from the claim text.