知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

68 records (took 0.022 seconds)

    MOTION REPRESENTATIONS FOR ARTICULATED ANIMATION
    23.
    发明申请
    MOTION REPRESENTATIONS FOR ARTICULATED ANIMATION 有权

    公开(公告)号：US20210407163A1

    公开(公告)日：2021-12-30

    申请号：US17364218

    申请日：2021-06-30

    Applicant: Snap Inc.

    Inventor： Menglei Chai ,  Jian Ren ,  Aliaksandr Siarohin ,  Sergey Tulyakov ,  Oliver Woodford

    IPC: G06T13/00 ,  G06T7/20 ,  G06T11/00 ,  G06N3/04 ,  G06N3/08

    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.

    CLOUD BASED MACHINE LEARNING
    25.
    发明申请
    CLOUD BASED MACHINE LEARNING 有权

    公开(公告)号：US20250124353A1

    公开(公告)日：2025-04-17

    申请号：US18988401

    申请日：2024-12-19

    Applicant: Snap Inc.

    Inventor： Eric Buehl ,  Jordan Hurwitz ,  Sergey Tulyakov ,  Shubham Vij

    IPC: G06N20/00 ,  G06F9/445 ,  H04L67/10

    Abstract: Disclosed are various embodiments for implementing computational tasks in a cloud environment in one or more operating system level virtualized containers. A parameter file can specify different parameters including hardware parameters, library parameters, user code parameters, and job parameters (e.g., sets of hyperparameters). The parameter file can be converted via a mapping and implemented in a cloud-based container platform.

    Optimizer based prunner for neural networks
    26.
    发明授权
    Optimizer based prunner for neural networks 有权

    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.

    COMPRESSING IMAGE-TO-IMAGE MODELS WITH AVERAGE SMOOTHING
    28.
    发明申请
    COMPRESSING IMAGE-TO-IMAGE MODELS WITH AVERAGE SMOOTHING 有权

    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

    IPC: G06T9/00 ,  G06N3/08

    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.

    AUTODECODING LATENT 3D DIFFUSION MODELS
    30.
    发明申请
    AUTODECODING LATENT 3D DIFFUSION MODELS 有权

    公开(公告)号：US20240420407A1

    公开(公告)日：2024-12-19

    申请号：US18211149

    申请日：2023-06-16

    Applicant: Snap Inc.

    Inventor： Evangelos Ntavelis ,  Kyle Olszewski ,  Aliaksandr Siarohin ,  Sergey Tulyakov

    IPC: G06T15/08 ,  G06N3/0455 ,  G06N3/08 ,  G06T9/00 ,  G06T15/20 ,  G06T19/20

    Abstract: Systems and methods for generating static and articulated 3D assets are provided that include a 3D autodecoder at their core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. The appropriate intermediate volumetric latent space is then identified and robust normalization and de-normalization operations are implemented to learn a 3D diffusion from 2D images or monocular videos of rigid or articulated objects. The methods are flexible enough to use either existing camera supervision or no camera information at all—instead efficiently learning the camera information during training. The generated results are shown to outperform state-of-the-art alternatives on various benchmark datasets and metrics, including multi-view image datasets of synthetic objects, real in-the-wild videos of moving people, and a large-scale, real video dataset of static objects.

Patent Agency Ranking