公开(公告)号：US20230118460A1

公开(公告)日：2023-04-20

申请号：US17968634

申请日：2022-10-18

Applicant: Google LLC

Inventor： Orly LIBA ,  Nikhil KARNAD ,  Nori KANAZAWA ,  Yael Pritch KNAAN ,  Huizhong CHEN ,  Longqi CAI

IPC: G06V10/26 ,  G06V10/774 ,  G06V10/764 ,  G06V20/20 ,  G06T5/00 ,  G06T11/00 ,  G06T5/20

Abstract: A media application generates training data that includes a first set of media items and a second set of media items, where the first set of media items correspond to the second set of media items and include distracting objects that are manually segmented. The media application trains a segmentation machine-learning model based on the training data to receive a media item with one or more distracting objects and to output a segmentation mask for one or more segmented objects that correspond to the one or more distracting objects.

公开(公告)号：US20230118361A1

公开(公告)日：2023-04-20

申请号：US17968645

申请日：2022-10-18

Applicant: Google LLC

Inventor： Orly LIBA ,  Navin SARMA ,  Yael Pritch KNAAN ,  Alexander SCHIFFHAUER ,  Longqi CAI ,  David JACOBS ,  Huizhong CHEN ,  Siyang LI ,  Bryan FELDMAN

IPC: G06T3/40 ,  G06T7/11 ,  G06T5/00

Abstract: A media application receives user input that indicates one or more objects to be erased from a media item. The media application translates the user input to a bounding box. The media application provides a crop of the media item based on the bounding box to a segmentation machine-learning model. The segmentation machine-learning model outputs a segmentation mask for one or more segmented objects in the crop of the media item and a corresponding segmentation score that indicates a quality of the segmentation mask.