中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.016 seconds)

    MULTI-DIMENSIONAL GENERATIVE FRAMEWORK FOR VIDEO GENERATION
    2.
    发明公开
    MULTI-DIMENSIONAL GENERATIVE FRAMEWORK FOR VIDEO GENERATION 审中-公开

    公开(公告)号：US20240193412A1

    公开(公告)日：2024-06-13

    申请号：US18063843

    申请日：2022-12-09

    Applicant: Lemon Inc.

    Inventor： Song Bai ,  Zhongcong Xu ,  Jiashi Feng ,  Jun Hao Liew ,  Wenqing Zhang

    IPC: G06N3/08

    CPC classification number: G06N3/08 ,  G06T2207/20081

    Abstract: Generating a multi-dimensional video using a multi-dimensional video generative model for, including, but not limited to, at least one of static portrait animation, video reconstruction, or motion editing. The method including providing data into the multi-dimensionally aware generator of the multi-dimensional video generative model, and generating the multi-dimensional video from the data by the multi-dimensionally aware generator. The generating of the multi-dimensional video includes inverting the data into a latent space of the multi-dimensionally aware generator, synthesizing content of the multi-dimensional video using an appearance component of the multi-dimensionally aware generator and corresponding camera pose and formulating an intermediate appearance code, developing a synthesis layer for encoding a motion component of the multi-dimensionally aware generator at a plurality of timesteps and formulating an intermediate motion code, introducing temporal dynamics into the intermediate appearance code and the intermediate motion code, and generating multi-dimensionally aware spatio-temporal representations of the data.

    CUSTOMIZING GENERATION OF OBJECTS USING DIFFUSION MODELS
    4.
    发明申请
    CUSTOMIZING GENERATION OF OBJECTS USING DIFFUSION MODELS 有权

    公开(公告)号：US20250014233A1

    公开(公告)日：2025-01-09

    申请号：US18347366

    申请日：2023-07-05

    Applicant: Lemon Inc.

    Inventor： Jiachun Pan ,  Hanshu Yan ,  Jiashi Feng ,  Jun Hao Liew

    IPC: G06T11/00 ,  G06T5/00

    Abstract: Methods of customizing generation of objects using diffusion models are provided. One or more parameters (e.g., a conditioning signal, network weights, or an initial or starting noise) of the diffusion model can be optimized by a backpropagation process, which can be performed by solving an augmented adjoint ordinary differential equation (ODE) based on an adjoint sensitivity method. The customized diffusion model can generate stylized objects, generate objects with specific visual effect(s), and provide adversary examples to audit security of an object generation system.

    MULTI-DIMENSIONAL IMAGE STYLIZATION USING TRANSFER LEARNING
    5.
    发明公开
    MULTI-DIMENSIONAL IMAGE STYLIZATION USING TRANSFER LEARNING 审中-公开

    公开(公告)号：US20240273871A1

    公开(公告)日：2024-08-15

    申请号：US18168867

    申请日：2023-02-14

    Applicant: Lemon Inc.

    Inventor： Guoxian Song ,  Hongyi Xu ,  Jing Liu ,  Tiancheng Zhi ,  Yichun Shi ,  Jianfeng Zhang ,  Zihang Jiang ,  Jiashi Feng ,  Shen Sang ,  Linjie Luo

    IPC: G06V10/77 ,  G06V10/28 ,  G06V10/44

    CPC classification number: G06V10/7715 ,  G06V10/28 ,  G06V10/454

    Abstract: A method for generating a multi-dimensional stylized image. The method includes providing input data into a latent space for a style conditioned multi-dimensional generator of a multi-dimensional generative model and generating the multi-dimensional stylized image from the input data by the style conditioned multi-dimensional generator. The method further includes synthesizing content for the multi-dimensional stylized image using a latent code and corresponding camera pose from the latent space to formulate an intermediate code to modulate synthesis convolution layers to generate feature images as multi-planar representations and synthesizing stylized feature images of the feature images for generating the multi-dimensional stylized image of the input data. The style conditioned multi-dimensional generator is tuned using a guided transfer learning process using a style prior generator.

    VIDEO GENERATION WITH LATENT DIFFUSION MODELS
    6.
    发明公开
    VIDEO GENERATION WITH LATENT DIFFUSION MODELS 审中-公开

    公开(公告)号：US20240169479A1

    公开(公告)日：2024-05-23

    申请号：US18056444

    申请日：2022-11-17

    Applicant: Lemon Inc.

    Inventor： Wei Min Wang ,  Daquan Zhou ,  Jiashi Feng

    IPC: G06T3/40

    CPC classification number: G06T3/4007 ,  G06T3/4053

    Abstract: The present disclosure provides systems and methods for video generation using latent diffusion machine learning models. Given a text input, video data relevant to the text input can be generated using a latent diffusion model. The process includes generating a predetermined number of key frames using text-to-image generation tasks performed within a latent space via a variational auto-encoder, enabling faster training and sampling times compared to pixel space-based diffusion models. The process further includes utilizing two-dimensional convolutions and associated adaptors to learn features for a given frame. Temporal information for the frames can be learned via a directed temporal attention module used to capture the relation among frames and to generate a temporally meaningful sequence of frames. Additional frames can be generated via a frame interpolation process for inserting one or more transition frames between two generated frames. The process can also include a super-resolution process for upsampling the frames.

    AUTOMATICALLY AND EFFICIENTLY GENERATING SEARCH SPACES FOR NEURAL NETWORK
    8.
    发明申请
    AUTOMATICALLY AND EFFICIENTLY GENERATING SEARCH SPACES FOR NEURAL NETWORK 有权

    公开(公告)号：US20220398450A1

    公开(公告)日：2022-12-15

    申请号：US17348246

    申请日：2021-06-15

    Applicant: Lemon Inc.

    Inventor： Xiaojie JIN ,  Daquan Zhou ,  Xiaochen Lian ,  Linjie Yang ,  Jiashi Feng

    IPC: G06N3/08 ,  G06N3/12

    Abstract: A super-network comprising a plurality of layers may be generated. Each layer may comprise cells with different structures. A predetermined number of cells from each layer may be selected. A plurality of cells may be generated based on selected cells using a local mutation model, wherein the local mutation model comprises a mutation window for removing redundant edges from each selected cell. Performance of the plurality of cells may be evaluated using a differentiable fitness scoring function. The operations of the generating a plurality of cells using the local mutation model, the evaluating performance of the plurality of cells using the differentiable fitness scoring function and the selecting the subset of cells based on the evaluation results may be iteratively performed until the super-network converges. A search space for each layer may be generated based on a predetermined top number of cells with largest fitness scores after the super-network converges.

Patent Agency Ranking