公开(公告)号：US20240046532A1

公开(公告)日：2024-02-08

申请号：US18489539

申请日：2023-10-18

Applicant: Google LLC

Inventor： Kfir Aberman ,  Yael Pritch Knaan ,  Orly Liba ,  David Edward Jacobs

IPC: G06T11/00 ,  G06N20/00 ,  G06T5/00 ,  G06T11/60

CPC classification number: G06T11/001 ,  G06N20/00 ,  G06T5/005 ,  G06T11/60

Abstract: Techniques for reducing a distractor object in a first image are presented herein. A system can access a mask and the first image. A distractor object in the first image can be inside a region of interest and can have a pixel with an original attribute. Additionally, the system can process, using a machine-learned inpainting model, the first image and the mask to generate an inpainted image. The pixel of the distractor object in the inpainted image can have an inpainted attribute in chromaticity channels. Moreover, the system can determine a palette transform based on a comparison of the first image and the inpainted image. The transform attribute can be different from the inpainted attribute. Furthermore, the system can process the first image to generate a recolorized image. The pixel in the recolorized image can have a recolorized attribute based on the transform attribute of the palette transform.

公开(公告)号：US11854120B2

公开(公告)日：2023-12-26

申请号：US17487741

申请日：2021-09-28

Applicant: Google LLC

Inventor： Kfir Aberman ,  Yael Pritch Knaan ,  David Edward Jacobs ,  Orly Liba

IPC: G06T11/00 ,  G06N20/00 ,  G06T5/00 ,  G06T11/60

CPC classification number: G06T11/001 ,  G06N20/00 ,  G06T5/005 ,  G06T11/60

Abstract: Techniques for reducing a distractor object in a first image are presented herein. A system can access a mask and the first image. A distractor object in the first image can be inside a region of interest and can have a pixel with an original attribute. Additionally, the system can process, using a machine-learned inpainting model, the first image and the mask to generate an inpainted image. The pixel of the distractor object in the inpainted image can have an inpainted attribute in chromaticity channels. Moreover, the system can determine a palette transform based on a comparison of the first image and the inpainted image. The transform attribute can be different from the inpainted attribute. Furthermore, the system can process the first image to generate a recolorized image. The pixel in the recolorized image can have a recolorized attribute based on the transform attribute of the palette transform.

公开(公告)号：US11721007B2

公开(公告)日：2023-08-08

申请号：US17982842

申请日：2022-11-08

Applicant: Google LLC

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

IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40

CPC classification number: G06T5/50 ,  G06T3/40 ,  G06T5/001 ,  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：US20230222636A1

公开(公告)日：2023-07-13

申请号：US17982842

申请日：2022-11-08

Applicant: Google LLC

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

IPC: G06T5/50 ,  G06T3/40 ,  G06T5/00

CPC classification number: G06T5/50 ,  G06T3/40 ,  G06T5/001 ,  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.