-
公开(公告)号：US20230094723A1
公开(公告)日：2023-03-30
申请号：US17487741
申请日：2021-09-28
Applicant: Google LLC
Inventor： Kfir Aberman , Yael Pritch Knaan , David Edward Jacobs , Orly Liba
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：US12266113B2
公开(公告)日：2025-04-01
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 , G06T5/60 , G06T5/70 , G06T5/94 , 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.
-
公开(公告)号：US20240355107A1
公开(公告)日：2024-10-24
申请号：US18684883
申请日：2021-08-23
Applicant: Google LLC
Inventor： Orly Liba , Michael Garth Milne , Navin Padman Sarma , Doron Kukliansky , Huizhong Chen , Yael Pritch Knaan
CPC classification number: G06V10/82 , G06T5/60 , G06V10/462 , G06T2207/20084 , G06T2207/20132 , G06V2201/07 , G06V2201/10
Abstract: A method includes receiving training data comprising a plurality of images. one or more identified objects in each of the plurality of images. and a detection score associated with each of the one or more identified objects. wherein the detection score for an object is indicative of a degree to which a portion of an image corresponds to the object. The method also includes training a neural network based on the training data to predict a distractor score for at least one object of the one or more identified objects in an input image, wherein the at least one object is selected based on an associated detection score, and wherein the distractor score for the at least one object is indicative of a perceived visual distraction caused by a presence of the at least one object in the input image. The method additionally includes outputting the trained neural network.
-
公开(公告)号：US20230037958A1
公开(公告)日：2023-02-09
申请号：US17786065
申请日：2020-12-24
Applicant: GOOGLE LLC
Inventor： Orly Liba , Rahul Garg , Neal Wadhwa , Jon Barron , Hayato Ikoma
IPC: G06T7/50
Abstract: A system includes a computing device. The computing device is configured to perform a set of functions. The set of functions includes receiving an image, wherein the image comprises a two-dimensional array of data. The set of functions includes extracting, by a two-dimensional neural network, a plurality of two-dimensional features from the two-dimensional array of data. The set of functions includes generating a linear combination of the plurality of two-dimensional features to form a single three-dimensional input feature. The set of functions includes extracting, by a three-dimensional neural network, a plurality of three-dimensional features from the single three-dimensional input feature. The set of functions includes determining a two-dimensional depth map. The two-dimensional depth map contains depth information corresponding to the plurality of three-dimensional features.
-
公开(公告)号：US20250037251A1
公开(公告)日：2025-01-30
申请号：US18717098
申请日：2022-01-13
Applicant: Google LLC
Inventor： Orly Liba , Kfir Aberman , Wei Xiong , David Futschik , Yael Pritch Knaan , Daniel Sýkora , Tianfan Xue
Abstract: A method includes obtaining an input image having a region to be inpainted, an indication of the region to be inpainted, and a guide image. The method also includes determining, by an encoder model, a first latent representation of the input image and a second latent representation of the guide image, and generating a combined latent representation based on the first latent representation and the second latent representation. The method additionally includes generating, by a style generative adversarial network model and based on the combined latent representation, an intermediate output image that includes inpainted image content for the region to be inpainted in the input image. The method further includes generating, based on the input image, the indication of the region, and the intermediate output image, an output image representing the input image with the region to be inpainted including the inpainted image content from the intermediate output image.
-
Patent Agency Ranking
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
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
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
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
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：US20250069194A1
公开(公告)日：2025-02-27
申请号：US18946147
申请日：2024-11-13
Applicant: Google LLC
Inventor： Kfir Aberman , Yotam Nitzan , Orly Liba , Yael Pritch Knaan , Qiurui He , Inbar Mosseri , Yossi Gandelsman , Michal Yarom
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.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.019 seconds)
