公开(公告)号：US12254412B2

公开(公告)日：2025-03-18

申请号：US18096338

申请日：2023-01-12

Applicant: Snap Inc.

Inventor： Enxu Yan ,  Sergey Tulyakov ,  Aleksei Podkin ,  Aleksei Stoliar

IPC: G06N3/082 ,  G06F17/16 ,  G06N3/04 ,  G06T7/10

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：US20250086466A1

公开(公告)日：2025-03-13

申请号：US18955297

申请日：2024-11-21

Applicant: Snap Inc.

Inventor： Sergey Tulyakov ,  Sergei Korolev ,  Aleksei Stoliar ,  Maksim Gusarov ,  Sergei Kotcur ,  Christopher Yale Crutchfield ,  Andrew Wan

IPC: G06N3/088 ,  G06F18/21 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778 ,  G06V10/82

Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.

公开(公告)号：US12182722B2

公开(公告)日：2024-12-31

申请号：US18213145

申请日：2023-06-22

Applicant: Snap Inc.

Inventor： Sergey Tulyakov ,  Sergei Korolev ,  Aleksei Stoliar ,  Maksim Gusarov ,  Sergei Kotcur ,  Christopher Yale Crutchfield ,  Andrew Wan

IPC: G06N3/088 ,  G06F18/21 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778 ,  G06V10/82

Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.

公开(公告)号：US20240354641A1

公开(公告)日：2024-10-24

申请号：US18613645

申请日：2024-03-22

Applicant: Snap Inc.

Inventor： William Miles Miller ,  Aleksei Stoliar

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Described is a system for gathering interaction data from use of one or more interaction functions by a first user, wherein the interaction data includes data in different modalities and generating a multimodal memory for the interaction data by applying the interaction data to a first machine learning model. The system also identifies a prompt for the first user and processes a combination of data associated with the prompt and the multimodal memory using a second machine learning model to generate recommended content for the first user. The system then proceeds to apply the recommended content to a first interaction client of the first user.

公开(公告)号：US12094135B2

公开(公告)日：2024-09-17

申请号：US17829644

申请日：2022-06-01

Applicant: Snap Inc.

Inventor： Sergey Tulyakov ,  Roman Furko ,  Aleksei Stoliar

IPC: G06T7/277 ,  G06F18/214 ,  G06T7/246 ,  G06T7/73 ,  G06T11/60 ,  G06V10/25 ,  G06V10/62 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V20/20 ,  G06V20/40 ,  G06V40/10 ,  G06V40/16

CPC classification number: G06T7/277 ,  G06F18/2148 ,  G06F18/2155 ,  G06T7/246 ,  G06T7/73 ,  G06T11/60 ,  G06V10/25 ,  G06V10/764 ,  G06V10/7747 ,  G06V10/7753 ,  G06V10/776 ,  G06V10/82 ,  G06V20/20 ,  G06V20/40 ,  G06V40/10 ,  G06V40/168 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06V10/62 ,  G06V2201/07

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：US20240296645A1

公开(公告)日：2024-09-05

申请号：US18664596

申请日：2024-05-15

Applicant: Snap Inc.

Inventor： Vladislav Shakhrai ,  Sergey Demyanov ,  Mikhail Vasilkovskii ,  Aleksei Stoliar

IPC: G06T19/20 ,  G06T7/40 ,  G06T11/00 ,  G06T17/20

CPC classification number: G06T19/20 ,  G06T7/40 ,  G06T11/001 ,  G06T17/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2210/12 ,  G06T2210/22 ,  G06T2219/2016

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.

公开(公告)号：US12020392B2

公开(公告)日：2024-06-25

申请号：US17855179

申请日：2022-06-30

Applicant: Snap Inc.

Inventor： Vladislav Shakhrai ,  Sergey Demyanov ,  Mikhail Vasilkovskii ,  Aleksei Stoliar

IPC: G06T19/00 ,  G06T7/40 ,  G06T11/00 ,  G06T17/20 ,  G06T19/20

CPC classification number: G06T19/20 ,  G06T7/40 ,  G06T11/001 ,  G06T17/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2210/12 ,  G06T2210/22 ,  G06T2219/2016

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.

公开(公告)号：US10909357B1

公开(公告)日：2021-02-02

申请号：US16277710

申请日：2019-02-15

Applicant: Snap Inc.

Inventor： Sergey Tulyakov ,  Roman Furko ,  Aleksei Stoliar

IPC: G06K9/00 ,  G06K9/62 ,  G06T7/246 ,  G06T7/73 ,  G06T11/60

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：US20240394933A1

公开(公告)日：2024-11-28

申请号：US18596452

申请日：2024-03-05

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

IPC: G06T11/00

Abstract: Described is a system for improving machine learning models by accessing a first latent diffusion machine learning model, 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 latent features, processing the noise data via the second latent diffusion machine learning model to generate one or more second latent features, and inputting the one or more first latent features and the one or more second latent features into a loss function. The system then modifies a parameter of the second latent diffusion machine learning model based on the output of the loss function.

公开(公告)号：US11736717B2

公开(公告)日：2023-08-22

申请号：US17490277

申请日：2021-09-30

Applicant: Snap Inc.

Inventor： Sergey Demyanov ,  Andrew Cheng-min Lin ,  Walton Lin ,  Aleksei Podkin ,  Aleksei Stoliar ,  Sergey Tulyakov

IPC: H04N19/54 ,  H04N19/137 ,  H04N19/149 ,  H04N19/172 ,  H04L65/70 ,  G06N3/045

CPC classification number: H04N19/54 ,  G06N3/045 ,  H04L65/70 ,  H04N19/137 ,  H04N19/149 ,  H04N19/172

Abstract: Systems and methods herein describe a video compression system. The described systems and methods accesses a sequence of image frames from a first computing device, the sequence of image frames comprising a first image frame and a second image frame, detects a first set of keypoints for the first image frame, transmits the first image frame and the first set of keypoints to a second computing device, detects a second set of keypoints for the second image frame, transmits the second set of keypoints to the second computing device, causes an animated image to be displayed on the second computing device.