知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.017 seconds)

    Generation of stylized drawing of three-dimensional shapes using neural networks
    2.
    发明授权
    Generation of stylized drawing of three-dimensional shapes using neural networks 有权

    公开(公告)号：US11880913B2

    公开(公告)日：2024-01-23

    申请号：US17452568

    申请日：2021-10-27

    Applicant: Adobe Inc. ,  University of Massachusetts

    Inventor： Aaron Hertzmann ,  Matthew Fisher ,  Difan Liu ,  Evangelos Kalogerakis

    IPC: G06T11/00 ,  G06T11/20 ,  G06N3/045

    CPC classification number: G06T11/001 ,  G06N3/045 ,  G06T11/203 ,  G06T2200/04

    Abstract: Techniques for generating a stylized drawing of three-dimensional (3D) shapes using neural networks are disclosed. A processing device generates a set of vector curve paths from a viewpoint of a 3D shape; extracts, using a first neural network of a plurality of neural networks of a machine learning model, surface geometry features of the 3D shape based on geometric properties of surface points of the 3D shape; determines, using a second neural network of the plurality of neural networks of the machine learning model, a set of at least one predicted stroke attribute based on the surface geometry features and a predetermined drawing style; generates, based on the at least one predicted stroke attribute, a set of vector stroke paths corresponding to the set of vector curve paths; and outputs a two-dimensional (2D) stylized stroke drawing of the 3D shape based at least on the set of vector stroke paths.

    GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS
    4.
    发明公开
    GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20240161355A1

    公开(公告)日：2024-05-16

    申请号：US18419287

    申请日：2024-01-22

    Applicant: Adobe Inc. ,  University of Massachusetts

    Inventor： Aaron Hertzmann ,  Matthew Fisher ,  Difan Liu ,  Evangelos Kalogerakis

    IPC: G06T11/00 ,  G06N3/045 ,  G06T11/20

    CPC classification number: G06T11/001 ,  G06N3/045 ,  G06T11/203 ,  G06T2200/04

    Abstract: Techniques for generating a stylized drawing of three-dimensional (3D) shapes using neural networks are disclosed. A processing device generates a set of vector curve paths from a viewpoint of a 3D shape; extracts, using a first neural network of a plurality of neural networks of a machine learning model, surface geometry features of the 3D shape based on geometric properties of surface points of the 3D shape; determines, using a second neural network of the plurality of neural networks of the machine learning model, a set of at least one predicted stroke attribute based on the surface geometry features and a predetermined drawing style; generates, based on the at least one predicted stroke attribute, a set of vector stroke paths corresponding to the set of vector curve paths; and outputs a two-dimensional (2D) stylized stroke drawing of the 3D shape based at least on the set of vector stroke paths.

    VECTOR FONT GENERATION BASED ON CASCADED DIFFUSION
    5.
    发明申请
    VECTOR FONT GENERATION BASED ON CASCADED DIFFUSION 有权

    公开(公告)号：US20250124212A1

    公开(公告)日：2025-04-17

    申请号：US18507847

    申请日：2023-11-13

    Applicant: Adobe Inc.

    Inventor： Difan Liu ,  Matthew David Fisher ,  Michaël Yanis Gharbi ,  Oliver Wang ,  Alec Stefan Jacobson ,  Vikas Thamizharasan ,  Evangelos Kalogerakis

    IPC: G06F40/109 ,  G06T11/20 ,  G06T11/40

    Abstract: In implementation of techniques for vector font generation based on cascaded diffusion, a computing device implements a glyph generation system to receive a sample glyph in a target font and a target glyph identifier. The glyph generation system generates a rasterized glyph in the target font using a raster diffusion model based on the sample glyph and the target glyph identifier, the rasterized glyph having a first level of resolution. The glyph generation system then generates a vector glyph using a vector diffusion model by vectorizing the rasterized glyph, the vector glyph having a second level of resolution different than the first level of resolution. The glyph generation system then displays the vector glyph in a user interface.

    VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS
    6.
    发明申请
    VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS 有权

    公开(公告)号：US20250119624A1

    公开(公告)日：2025-04-10

    申请号：US18894443

    申请日：2024-09-24

    Applicant: ADOBE INC.

    Inventor： Seoung Wug Oh ,  Mingi Kwon ,  Joon-Young Lee ,  Yang Zhou ,  Difan Liu ,  Haoran Cai ,  Baqiao Liu ,  Feng Liu

    IPC: H04N21/81

    Abstract: A method, apparatus, non-transitory computer readable medium, and system for generating synthetic videos includes obtaining an input prompt describing a video scene. The embodiments then generate a plurality of frame-wise token embeddings corresponding to a sequence of video frames, respectively, based on the input prompt. Subsequently, embodiments generate, using a video generation model, a synthesized video depicting the video scene. The synthesized includes a plurality of images corresponding to the sequence of video frames.

    HYBRID SAMPLING FOR DIFFUSION MODELS
    7.
    发明申请
    HYBRID SAMPLING FOR DIFFUSION MODELS 有权

    公开(公告)号：US20250061548A1

    公开(公告)日：2025-02-20

    申请号：US18452150

    申请日：2023-08-18

    Applicant: ADOBE INC.

    Inventor： Difan Liu ,  Siddharth Iyer ,  Ryan Joe Murdock

    IPC: G06T5/00 ,  G06T5/50

    Abstract: Systems and methods for generating images using hybrid sampling include obtaining a noisy image and generating a first denoised image during a first reverse diffusion phase using a diffusion neural network. The first denoised image is generated based on a first sampler that uses a first sampling density during at least a portion of the first reverse diffusion phase. Subsequently, a second denoised image is generated based on the first denoised image during a second reverse diffusion phase using the diffusion neural network. The second denoised image is generated based on a second sampler that uses a second sampling density different from the first sampling density during at least a portion of the second reverse diffusion phase.

    Semantic Image Fill at High Resolutions
    8.
    发明公开
    Semantic Image Fill at High Resolutions 审中-公开

    公开(公告)号：US20230360376A1

    公开(公告)日：2023-11-09

    申请号：US17744995

    申请日：2022-05-16

    Applicant: Adobe Inc.

    Inventor： Tobias Hinz ,  Taesung Park ,  Richard Zhang ,  Matthew David Fisher ,  Difan Liu ,  Evangelos Kalogerakis

    IPC: G06V10/774 ,  G06V10/22 ,  G06T3/40

    CPC classification number: G06V10/7753 ,  G06V10/235 ,  G06T3/4046

    Abstract: Semantic fill techniques are described that support generating fill and editing images from semantic inputs. A user input, for example, is received by a semantic fill system that indicates a selection of a first region of a digital image and a corresponding semantic label. The user input is utilized by the semantic fill system to generate a guidance attention map of the digital image. The semantic fill system leverages the guidance attention map to generate a sparse attention map of a second region of the digital image. A semantic fill of pixels is generated for the first region based on the semantic label and the sparse attention map. The edited digital image is displayed in a user interface.

    GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS
    9.
    发明申请
    GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS 有权

    公开(公告)号：US20230109732A1

    公开(公告)日：2023-04-13

    申请号：US17452568

    申请日：2021-10-27

    Applicant: Adobe Inc. ,  University of Massachusetts

    Inventor： Aaron Hertzmann ,  Matthew Fisher ,  Difan Liu ,  Evangelos Kalogerakis

    IPC: G06T11/00 ,  G06T11/20 ,  G06N3/04

    Abstract: Techniques for generating a stylized drawing of three-dimensional (3D) shapes using neural networks are disclosed. A processing device generates a set of vector curve paths from a viewpoint of a 3D shape; extracts, using a first neural network of a plurality of neural networks of a machine learning model, surface geometry features of the 3D shape based on geometric properties of surface points of the 3D shape; determines, using a second neural network of the plurality of neural networks of the machine learning model, a set of at least one predicted stroke attribute based on the surface geometry features and a predetermined drawing style; generates, based on the at least one predicted stroke attribute, a set of vector stroke paths corresponding to the set of vector curve paths; and outputs a two-dimensional (2D) stylized stroke drawing of the 3D shape based at least on the set of vector stroke paths.

Patent Agency Ranking