公开(公告)号：US12217472B2

公开(公告)日：2025-02-04

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 ,  G06T5/20 ,  G06T5/77 ,  G06T5/94 ,  G06T11/00 ,  G06V10/764 ,  G06V10/774 ,  G06V20/20

Abstract: A media application generates training data that includes a first set of visual media items and a second set of visual media items, where the first set of visual media items correspond to the second set of visual 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 visual 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：US12169911B2

公开(公告)日：2024-12-17

申请号：US18334700

申请日：2023-06-14

Applicant: Google LLC

Inventor： Kfir Aberman ,  Yotam Nitzan ,  Orly Liba ,  Yael Pritch Knaan ,  Qiurui He ,  Inbar Mosseri ,  Yossi Gandelsman ,  Michal Yarom

IPC: G06T5/00 ,  G06T3/40 ,  G06T5/50

Abstract: Systems and methods for identifying a personalized prior within a generative model's latent vector space based on a set of images of a given subject. In some examples, the present technology may further include using the personalized prior to confine the inputs of a generative model to a latent vector space associated with the given subject, such that when the model is tasked with editing an image of the subject (e.g., to perform inpainting to fill in masked areas, improve resolution, or deblur the image), the subject's identifying features will be reflected in the images the model produces.

公开(公告)号：US20230325998A1

公开(公告)日：2023-10-12

申请号：US18334700

申请日：2023-06-14

Applicant: Google LLC

Inventor： Kfir Aberman ,  Yotam Nitzan ,  Orly Liba ,  Yael Pritch Knaan ,  Qiurui He ,  Inbar Mosseri ,  Yossi Gandelsman ,  Michal Yarom

IPC: G06T5/50 ,  G06T5/00 ,  G06T3/40

CPC classification number: G06T5/50 ,  G06T5/001 ,  G06T3/40 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for identifying a personalized prior within a generative model's latent vector space based on a set of images of a given subject. In some examples, the present technology may further include using the personalized prior to confine the inputs of a generative model to a latent vector space associated with the given subject, such that when the model is tasked with editing an image of the subject (e.g., to perform inpainting to fill in masked areas, improve resolution, or deblur the image), the subject's identifying features will be reflected in the images the model produces.

公开(公告)号：US20220230323A1

公开(公告)日：2022-07-21

申请号：US17617560

申请日：2019-07-15

Applicant: Google LLC

Inventor： Orly Liba ,  Florian Kainz ,  Longqi Cai ,  Yael Pritch Knaan

IPC: G06T7/11 ,  G06T5/00 ,  G06V10/764

Abstract: A device automatically segments an image into different regions and automatically adjusts perceived exposure-levels or other characteristics associated with each of the different regions, to produce pictures that exceed expectations for the type of optics and camera equipment being used and in some cases, the pictures even resemble other high-quality photography created using professional equipment and photo editing software. A machine-learned model is trained to automatically segment an image into distinct regions. The model outputs one or more masks that define the distinct regions. The mask(s) are refined using a guided filter or other technique to ensure that edges of the mask(s) conform to edges of objects depicted in the image. By applying the mask(s) to the image, the device can individually adjust respective characteristics of each of the different regions to produce a higher-quality picture of a scene.