Patents by Inventor Omid Poursaeed
Omid Poursaeed has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11869057Abstract: 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.Type: GrantFiled: December 1, 2021Date of Patent: January 9, 2024Assignee: eBay Inc.Inventors: Mohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
-
Patent number: 11403807Abstract: Certain embodiments involve techniques for generating a 3D representation based on a provided 2D image of an object. An image generation system receives the 2D image representation and generates a multi-dimensional vector of the input that represents the image. The image generation system samples a set of points and provides the set of points and the multi-dimensional vector to a neural network that was trained to predict a 3D surface representing the image such that the 3D surface is consistent with a 3D surface of the object calculated using an implicit function for representing the image. The neural network predicts, based on the multi-dimensional vector and the set of points, the 3D surface representing the object.Type: GrantFiled: February 24, 2020Date of Patent: August 2, 2022Assignee: Adobe Inc.Inventors: Vladimir Kim, Omid Poursaeed, Noam Aigerman, Matthew Fisher
-
Publication number: 20220092367Abstract: 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.Type: ApplicationFiled: December 1, 2021Publication date: March 24, 2022Applicant: eBay Inc.Inventors: Mohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
-
Patent number: 11222246Abstract: 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.Type: GrantFiled: January 3, 2020Date of Patent: January 11, 2022Assignee: eBay Inc.Inventors: Mohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
-
Publication number: 20210264659Abstract: Certain embodiments involve techniques for generating a 3D representation based on a provided 2D image of an object. An image generation system receives the 2D image representation and generates a multi-dimensional vector of the input that represents the image. The image generation system samples a set of points and provides the set of points and the multi-dimensional vector to a neural network that was trained to predict a 3D surface representing the image such that the 3D surface is consistent with a 3D surface of the object calculated using an implicit function for representing the image. The neural network predicts, based on the multi-dimensional vector and the set of points, the 3D surface representing the object.Type: ApplicationFiled: February 24, 2020Publication date: August 26, 2021Inventors: Vladimir Kim, Omid Poursaeed, Noam Aigerman, Matthew Fisher
-
Patent number: 10977549Abstract: In implementations of object animation using generative neural networks, one or more computing devices of a system implement an animation system for reproducing animation of an object in a digital video. A mesh of the object is obtained from a first frame of the digital video and a second frame of the digital video having the object is selected. Features of the object from the second frame are mapped to vertices of the mesh, and the mesh is warped based on the mapping. The warped mesh is rendered as an image by a neural renderer and compared to the object from the second frame to train a neural network. The rendered image is then refined by a generator of a generative adversarial network which includes a discriminator. The discriminator trains the generator to reproduce the object from the second frame as the refined image.Type: GrantFiled: February 14, 2019Date of Patent: April 13, 2021Assignee: Adobe Inc.Inventors: Vladimir Kim, Omid Poursaeed, Jun Saito, Elya Shechtman
-
Publication number: 20200265294Abstract: In implementations of object animation using generative neural networks, one or more computing devices of a system implement an animation system for reproducing animation of an object in a digital video. A mesh of the object is obtained from a first frame of the digital video and a second frame of the digital video having the object is selected. Features of the object from the second frame are mapped to vertices of the mesh, and the mesh is warped based on the mapping. The warped mesh is rendered as an image by a neural renderer and compared to the object from the second frame to train a neural network. The rendered image is then refined by a generator of a generative adversarial network which includes a discriminator. The discriminator trains the generator to reproduce the object from the second frame as the refined image.Type: ApplicationFiled: February 14, 2019Publication date: August 20, 2020Applicant: Adobe Inc.Inventors: Vladimir Kim, Omid Poursaeed, Jun Saito, Elya Shechtman
-
Publication number: 20200218947Abstract: 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.Type: ApplicationFiled: January 3, 2020Publication date: July 9, 2020Inventors: Mohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
-
Patent number: 10552714Abstract: 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.Type: GrantFiled: March 16, 2018Date of Patent: February 4, 2020Assignee: eBay Inc.Inventors: Mohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed
-
Publication number: 20190286950Abstract: 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.Type: ApplicationFiled: March 16, 2018Publication date: September 19, 2019Inventors: Mohammadhadi Kiapour, Shuai Zheng, Robinson Piramuthu, Omid Poursaeed