公开(公告)号：US20230260127A1

公开(公告)日：2023-08-17

申请号：US17650918

申请日：2022-02-14

Applicant: Snap Inc.

Inventor： Shani Ben Baruch ,  Ma'ayan Mishin Shuvi ,  Gal Dudovitch ,  Avihay Assouline ,  Itamar Berger ,  Gal Sasson

IPC: G06T7/11 ,  G06T11/00 ,  G06T5/00

CPC classification number: G06T7/11 ,  G06T11/00 ,  G06T5/005 ,  G06T2207/20092 ,  G06T2207/20081 ,  G06T2207/10016 ,  G06T2207/20132

Abstract: Methods and systems are disclosed for performing operations for segmenting an object. The operations include receiving an image that includes a depiction of a first object; receiving a first segmentation dataset; applying a first machine learning technique to the first segmentation dataset and the image to estimate a first segmentation of the first object depicted in the image; generating a second segmentation dataset that includes the estimated first segmentation and a correction to the estimated first segmentation of the first object; applying the first machine learning technique to the second segmentation dataset and the image to estimate a second segmentation of the first object depicted in the image; and applying an augmented reality experience to the image based on the estimated second segmentation of the first object.

公开(公告)号：US12159412B2

公开(公告)日：2024-12-03

申请号：US17650918

申请日：2022-02-14

Applicant: Snap Inc.

Inventor： Shani Ben Baruch ,  Ma'ayan Mishin Shuvi ,  Gal Dudovitch ,  Avihay Assouline ,  Itamar Berger ,  Gal Sasson

IPC: G06T7/11 ,  G06T5/77 ,  G06T11/00

Abstract: Methods and systems are disclosed for performing operations for segmenting an object. The operations include receiving an image that includes a depiction of a first object; receiving a first segmentation dataset; applying a first machine learning technique to the first segmentation dataset and the image to estimate a first segmentation of the first object depicted in the image; generating a second segmentation dataset that includes the estimated first segmentation and a correction to the estimated first segmentation of the first object; applying the first machine learning technique to the second segmentation dataset and the image to estimate a second segmentation of the first object depicted in the image; and applying an augmented reality experience to the image based on the estimated second segmentation of the first object.