-
公开(公告)号：US20250054199A1
公开(公告)日：2025-02-13
申请号：US18923108
申请日：2024-10-22
Applicant: Snap Inc.
Inventor： Jian Ren , Menglei Chai , Sergey Tulyakov , Qing Jin
Abstract: System and methods for compressing image-to-image models. Generative Adversarial Networks (GANs) have achieved success in generating high-fidelity images. An image compression system and method adds a novel variant to class-dependent parameters (CLADE), referred to as CLADE-Avg, which recovers the image quality without introducing extra computational cost. An extra layer of average smoothing is performed between the parameter and normalization layers. Compared to CLADE, this image compression system and method smooths abrupt boundaries, and introduces more possible values for the scaling and shift. In addition, the kernel size for the average smoothing can be selected as a hyperparameter, such as a 3×3 kernel size. This method does not introduce extra multiplications but only addition, and thus does not introduce much computational overhead, as the division can be absorbed into the parameters after training.
-
公开(公告)号：US20240282066A1
公开(公告)日：2024-08-22
申请号：US18653609
申请日：2024-05-02
Applicant: Snap Inc.
Inventor： Artem Bondich , Menglei Chai , Olekssandr Pyshchenko , Jian Ren , Sergey Tulyakov
CPC classification number: G06T19/006 , G06F18/214 , G06N3/045 , G06N3/08 , G06T7/251 , G06T17/00 , G06T19/20 , G06T2207/20081 , G06T2207/20084 , G06T2215/16 , G06T2219/024 , G06T2219/2024
Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.
-
公开(公告)号：US11887357B2
公开(公告)日：2024-01-30
申请号：US17547548
申请日：2021-12-10
Applicant: Snap Inc.
Inventor： Jianchao Yang , Ning Xu , Jian Ren
IPC: G06K9/62 , G06V10/774 , G06F18/214 , G06F18/24 , G06F18/21 , G06F18/25 , G06V30/19 , G06V10/776 , G06V10/82 , H04L51/212
CPC classification number: G06V10/7753 , G06F18/217 , G06F18/2155 , G06F18/24 , G06F18/254 , G06V10/776 , G06V10/82 , G06V30/1916 , G06V30/19173 , H04L51/212
Abstract: Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.
-
公开(公告)号：US11798213B2
公开(公告)日：2023-10-24
申请号：US17364218
申请日：2021-06-30
Applicant: Snap Inc.
Inventor： Menglei Chai , Jian Ren , Aliaksandr Siarohin , Sergey Tulyakov , Oliver Woodford
CPC classification number: G06T13/00 , G06N3/045 , G06N3/08 , G06T7/20 , G06T11/001 , G06T2207/20081 , G06T2207/20084
Abstract: Systems and methods herein describe novel motion representations for animating articulated objects consisting of distinct parts. The described systems and method access source image data, identify driving image data to modify image feature data in the source image sequence data, generate, using an image transformation neural network, modified source image data comprising a plurality of modified source images depicting modified versions of the image feature data, the image transformation neural network being trained to identify, for each image in the source image data, a driving image from the driving image data, the identified driving image being implemented by the image transformation neural network to modify a corresponding source image in the source image data using motion estimation differences between the identified driving image and the corresponding source image, and stores the modified source image data.
-
5.发明申请公开(公告)号：US20220207875A1
公开(公告)日：2022-06-30
申请号：US17550852
申请日：2021-12-14
Applicant: Snap Inc.
Inventor： Kavya Venkata Kota Kopparapu , Benjamin Dodson , Francesc Xavier Drudis Rius , Angus Kong , Richard Leider , Jian Ren , Sergey Tulyakov , Jiayao Yu
Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.
-
Patent Agency Ranking
公开(公告)号：US12272015B2
公开(公告)日：2025-04-08
申请号：US18653609
申请日：2024-05-02
Applicant: Snap Inc.
Inventor： Artem Bondich , Menglei Chai , Oleksandr Pyshchenko , Jian Ren , Sergey Tulyakov
Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.
-
公开(公告)号：US20240296535A1
公开(公告)日：2024-09-05
申请号：US18176843
申请日：2023-03-01
Applicant: Snap Inc.
Inventor： Mykyta Bakunov , Arnab Ghosh , Pavel Savcenkov , Sergey Smetanin , Jian Ren
IPC: G06T7/00 , G06F40/126 , G06F40/40 , G06T11/00
CPC classification number: G06T7/0002 , G06F40/126 , G06F40/40 , G06T11/00 , G06T2207/20081 , G06T2207/20084 , G06T2207/30168
Abstract: Examples disclosed herein describe techniques for automatic image quality evaluation. A first set of images generated by a first automated image generator and a second set of images generated by a second automated image generator are accessed. A first machine learning model generates a first quality indicator for each image in the first set of images and the second set of images. A second machine learning model generates a second quality indicator for each image in the first set of images and the second set of images. Based on the generated indicators, a first image from the first set of images and a second image from the second set of images are automatically selected and compared. A first ranking of the first automated image generator and the second automated image generator is generated based on the comparison, and ranking data is caused to be presented on a device.
-
公开(公告)号：US20240273809A1
公开(公告)日：2024-08-15
申请号：US18644653
申请日：2024-04-24
Applicant: Snap Inc.
Inventor： Zeng Huang , Jian Ren , Sergey Tulyakov , Menglei Chai , Kyle Olszewski , Huan Wang
CPC classification number: G06T15/06 , G06T7/97 , G06T2207/20081 , G06T2207/20084
Abstract: Methods and systems are disclosed for performing operations for generating a 3D model of a scene. The operations include: receiving a set of two-dimensional (2D) images representing a first view of a real-world environment; applying a machine learning model comprising a neural light field network to the set of 2D images to predict pixel values of a target image representing a second view of the real-world environment, the machine learning model being trained to map a ray origin and direction directly to a given pixel value; and generating a three-dimensional (3D) model of the real-world environment based on the set of 2D images and the predicted target image.
-
公开(公告)号：US12002146B2
公开(公告)日：2024-06-04
申请号：US17656778
申请日：2022-03-28
Applicant: Snap Inc.
Inventor： Zeng Huang , Jian Ren , Sergey Tulyakov , Menglei Chai , Kyle Olszewski , Huan Wang
CPC classification number: G06T15/06 , G06T7/97 , G06T2207/20081 , G06T2207/20084
Abstract: Methods and systems are disclosed for performing operations for generating a 3D model of a scene. The operations include: receiving a set of two-dimensional (2D) images representing a first view of a real-world environment; applying a machine learning model comprising a neural light field network to the set of 2D images to predict pixel values of a target image representing a second view of the real-world environment, the machine learning model being trained to map a ray origin and direction directly to a given pixel value; and generating a three-dimensional (3D) model of the real-world environment based on the set of 2D images and the predicted target image.
-
公开(公告)号：US20230386158A1
公开(公告)日：2023-11-30
申请号：US17814391
申请日：2022-07-22
Applicant: Snap Inc.
Inventor： Menglei Chai , Sergey Tulyakov , Jian Ren , Hsin-Ying Lee , Kyle Olszewski , Zeng Huang , Zezhou Cheng
CPC classification number: G06T19/20 , G06T17/00 , G06T2219/2012 , G06T2219/2021
Abstract: Systems, computer readable media, and methods herein describe an editing system where a three-dimensional (3D) object can be edited by editing a 2D sketch or 2D RGB views of the 3D object. The editing system uses multi-modal (MM) variational auto-decoders (VADs)(MM-VADs) that are trained with a shared latent space that enables editing 3D objects by editing 2D sketches of the 3D objects. The system determines a latent code that corresponds to an edited or sketched 2D sketch. The latent code is then used to generate a 3D object using the MM-VADs with the latent code as input. The latent space is divided into a latent space for shapes and a latent space for colors. The MM-VADs are trained with variational auto-encoders (VAE) and a ground truth.
-
-
-
-
-
-
-
-
-
Search Results
36
records
(took 0.017 seconds)
