-
公开(公告)号：US11657479B2
公开(公告)日：2023-05-23
申请号：US17445362
申请日：2021-08-18
Applicant: Snap Inc.
Inventor： Sergey Demyanov , Aleksei Podkin , Aleksei Stoliar , Vadim Velicodnii , Fedor Zhdanov
CPC classification number: G06T5/001 , G06T5/10 , G06T2200/16 , G06T2207/10004 , G06T2207/20048 , G06T2207/20081 , G06T2207/30196 , H04L51/10
Abstract: A mobile device can implement a neural network-based domain transfer scheme to modify an image in a first domain appearance to a second domain appearance. The domain transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The domain transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.
-
公开(公告)号：US11580400B1
公开(公告)日：2023-02-14
申请号：US16586635
申请日：2019-09-27
Applicant: Snap Inc.
Inventor： Enxu Yan , Sergey Tulyakov , Aleksei Podkin , Aleksei Stoliar
Abstract: A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.
-
公开(公告)号：US20210383509A1
公开(公告)日：2021-12-09
申请号：US17445362
申请日：2021-08-18
Applicant: Snap Inc.
Inventor： Sergey Demyanov , Aleksei Podkin , Aleksei Stoliar , Vadim Velicodnii , Fedor Zhdanov
Abstract: A mobile device can implement a neural network-based domain transfer scheme to modify an image in a first domain appearance to a second domain appearance. The domain transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The domain transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.
-
公开(公告)号：US20210299630A1
公开(公告)日：2021-09-30
申请号：US17330852
申请日：2021-05-26
Applicant: Snap Inc.
Inventor： Grygoriy Kozhemiak , Oleksandr Pyshchenko , Victor Shaburov , Trevor Stephenson , Aleksei Stoliar
Abstract: Systems and methods are provided for receiving a first media content item associated with a first interactive object of an interactive message, receiving a second media content item associated with a second interactive object of the interactive message, generating a third media content item based on the first media content item and second media content item, wherein the third media content item comprises combined features of the first media content item and the second media content item, and causing display of the generated third media content item.
-
公开(公告)号：US11120526B1
公开(公告)日：2021-09-14
申请号：US16376564
申请日：2019-04-05
Applicant: Snap Inc.
Inventor： Sergey Demyanov , Aleksei Podkin , Aleksei Stoliar , Vadim Velicodnii , Fedor Zhdanov
Abstract: A mobile device can implement a neural network-based domain transfer scheme to modify an image in a first domain appearance to a second domain appearance. The domain transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The domain transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.
-
Patent Agency Ranking
公开(公告)号：US20210192198A1
公开(公告)日：2021-06-24
申请号：US17138177
申请日：2020-12-30
Applicant: Snap Inc.
Inventor： Sergey Tulyakov , Roman Furko , Aleksei Stoliar
Abstract: A landmark detection system can more accurately detect landmarks in images using a detection scheme that penalizes for dispersion parameters, such as variance or scale. The landmark detection system can be trained using both labeled and unlabeled training data in a semi-supervised approach. The landmark detection system can further implement tracking of an object across multiple images using landmark data.
-
公开(公告)号：US20240394843A1
公开(公告)日：2024-11-28
申请号：US18434411
申请日：2024-02-06
Applicant: Snap Inc.
Inventor： Pavlo Chemerys , Colin Eles , Ju Hu , Qing Jin , Yanyu Li , Ergeta Muca , Jian Ren , Dhritiman Sagar , Aleksei Stoliar , Sergey Tulyakov , Huan Wang
Abstract: Described is a system for improving machine learning models by accessing a first latent diffusion machine learning model, the first latent diffusion machine learning model trained to perform a first number of denoising steps, accessing a second latent diffusion machine learning model that was derived from the first latent diffusion machine learning model, the second latent diffusion machine learning model trained to perform a second number of denoising steps, generating noise data, processing the noise data via the first latent diffusion machine learning model to generate one or more first images, processing the noise data via the second latent diffusion machine learning model to generate one or more second images, and modify a parameter of the second latent diffusion machine learning model based on a comparison of the one or more first images with the one or more second images.
-
公开(公告)号：US20240355010A1
公开(公告)日：2024-10-24
申请号：US18529550
申请日：2023-12-05
Applicant: Snap Inc.
Inventor： Bohdan Ahafonov , Matthew Hallberg , Sergei Korolev , William Miles Miller , Daria Skrypnyk , Aleksei Stoliar
CPC classification number: G06T11/001 , G06T7/11 , G06T11/40 , G06T11/60 , G06V20/20 , G10L15/08 , G10L15/22 , G06T2210/16 , G10L2015/088
Abstract: Methods and systems are disclosed for generating an extended reality (XR) try-on experience. The methods and systems store, in a multimodal memory, interaction data representing use of one or more interaction functions including data in different modalities. The methods and systems detect an object depicted in an image captured by an interaction client and generate, by a machine learning model, a prompt based on the object depicted in the image and the interaction data in the multimodal memory. The methods and systems generate an artificial texture based on the prompt and modify a texture of the object depicted in the image using the artificial texture that has been generated based on the prompt.
-
公开(公告)号：US12125129B2
公开(公告)日：2024-10-22
申请号：US18136470
申请日：2023-04-19
Applicant: Snap Inc.
Inventor： Sergey Demyanov , Aleksei Podkin , Aliaksandr Siarohin , Aleksei Stoliar , Sergey Tulyakov
CPC classification number: G06T13/00 , G06N3/045 , G06N3/08 , G06V40/171 , G06V40/174
Abstract: Systems and methods are disclosed for generating, a source image sequence using an image sensor of the computing device, the source image sequence comprising a plurality of source images depicting a head and face, identifying driving image sequence data to modify face image feature data in the source image sequence, generating, using an image transformation neural network, a modified source image sequence comprising a plurality of modified source images depicting modified versions of the head and face, and storing the modified source image sequence on the computing device.
-
公开(公告)号：US20240005617A1
公开(公告)日：2024-01-04
申请号：US17855179
申请日：2022-06-30
Applicant: Snap Inc.
Inventor： Vladislav Shakhrai , Sergey Demyanov , Mikhail Vasilkovskii , Aleksei Stoliar
CPC classification number: G06T19/20 , G06T11/001 , G06T17/20 , G06T7/40 , G06T2219/2016 , G06T2210/12 , G06T2210/22 , G06T2207/20081 , G06T2207/20084
Abstract: Methods and systems are disclosed for performing operations for generating a photorealistic rendering of an object. The operations include: accessing a set of albedo textures and a machine learning model associated with a real-world object, the set of albedo textures and a machine learning model having been trained based on a plurality of viewpoints of the real-world object; obtaining a three-dimensional (3D) mesh of the real-world object; receiving input that selects a new viewpoint that differs from the plurality of viewpoints of the real-world object; and generating a photorealistic rendering of the real-world object from the new viewpoint based on the 3D mesh of the real-world object, the set of albedo textures, and the machine learning model associated with the real-world object.
-
-
-
-
-
-
-
-
-
Search Results
45
records
(took 0.021 seconds)
