公开(公告)号：US20240404005A1

公开(公告)日：2024-12-05

申请号：US18205674

申请日：2023-06-05

Applicant: Snap Inc.

Inventor： Jonathan Heimann ,  Nir Malbin ,  Avihay Assouline ,  Gal Sasson

IPC: G06T3/40 ,  G06T7/70 ,  G06T11/00 ,  G06T15/00 ,  G06V20/20

Abstract: Methods and systems are disclosed for generating high resolution images using lower resolution machine learning models. The system receives one or more images depicting a real-world object in a real-world scene and receives a source image depicting a fashion item comprising a target. The system processes, using one or more machine learning models, the one or more images together with the source image to generate a new image depicting the real-world object wearing the fashion item depicted in the source image, the new image having a lower image resolution than an image resolution of the source image. The system selectively blends pixels of the new image with pixels of the source image to generate a virtual extended reality (XR) experience.

公开(公告)号：US20240404278A1

公开(公告)日：2024-12-05

申请号：US18205696

申请日：2023-06-05

Applicant: Snap Inc.

Inventor： Jonathan Heimann ,  Nir Malbin ,  Avihay Assouline ,  Itamar Berger

IPC: G06V20/40 ,  G06V10/82

Abstract: Methods and systems are disclosed for applying machine learning models to compressed videos. The system receives a video, depicting an object, that has previously been compressed using one or more video compression processes. The system analyzes, using one or more machine learning models, the video that has previously been compressed to generate a prediction corresponding to the object depicted in the video, with one or more artifacts resulting from application of the one or more machine learning models to the video that has been previously compressed being absent from the prediction. The system generates a visual output based on the prediction in which the one or more artifacts are absent.

公开(公告)号：US20240355019A1

公开(公告)日：2024-10-24

申请号：US18304181

申请日：2023-04-20

Applicant: Snap Inc.

Inventor： Avihay Assouline ,  Itamar Berger ,  Jonathan Heimann

IPC: G06T11/60 ,  G06F40/20 ,  G06F40/40 ,  G06T7/10 ,  G06T7/60 ,  G06T11/00 ,  G06V10/776 ,  G06V20/20

CPC classification number: G06T11/60 ,  G06F40/20 ,  G06F40/40 ,  G06T7/10 ,  G06T7/60 ,  G06T11/001 ,  G06V10/776 ,  G06V20/20 ,  G06T2200/24 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/20132 ,  G06T2207/30201 ,  G06T2210/16 ,  G06T2210/22

Abstract: Methods and systems are disclosed for generating an extended reality (XR) try-on experience based on an image produced by a diffusion model. The system receives an image depicting a real-world object and generates a prompt comprising a textual description of a fashion item. The system analyzes the image and the textual description of the fashion item using a generative machine learning model to generate an artificial image that depicts an artificial object that resembles the real-world object wearing an artificial fashion item matching the textual description of the fashion item. The system identifies an object comprising a real-world product image that matches visual attributes of the artificial fashion item and replaces the artificial fashion item in the artificial image with the object to generate an output image.

公开(公告)号：US20250061662A1

公开(公告)日：2025-02-20

申请号：US18234471

申请日：2023-08-16

Applicant: Snap Inc.

Inventor： Avihay Assouline ,  Amir Fruchtman ,  Jonathan Heimann ,  Nir Malbin

IPC: G06T19/00 ,  G06T5/50 ,  G06T19/20

Abstract: Methods and systems are disclosed for using machine learning models to perform pixel-based deformation of fashion items. The methods and systems receive one or more images depicting a first person in a first pose and receive a source image depicting a target fashion item worn on a portion of a body of a second person in a second pose. The methods and systems process, using one or more machine learning models, the one or more images together with the source image to generate a flow field indicating existence and location of each pixel of the one or more images in the source image and modify, based on the flow field, a portion of the one or more images to overlay the target fashion item on the first person including one or more portions of the target fashion item that extend beyond a body of the first person.

公开(公告)号：US20240378763A1

公开(公告)日：2024-11-14

申请号：US18196160

申请日：2023-05-11

Applicant: Snap Inc.

Inventor： Avihay Assouline ,  Amir Fruchtman ,  Jonathan Heimann ,  Nir Malbin

IPC: G06T11/00 ,  G06T7/11

Abstract: Methods and systems are disclosed for generating an extended reality (XR) try-on experience based on an image produced by a diffusion model. The system receives a first image depicting a real-world object and receives a second image depicting a target fashion item. The system generates a warped image in which pixels of the target fashion item depicted in the second image replace pixels of a portion of the real-world object in the first image and generates one or more segmentation maps corresponding to incomplete portions of the warped image. The system analyzes the warped image and the one or more segmentation maps using a generative machine learning model to generate an artificial image that populates the incomplete portions of the warped image to depict the real-world object wearing the target fashion item.