中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

25 records (took 0.021 seconds)

    Semantic class localization digital environment
    2.
    发明专利
    Semantic class localization digital environment 未知

    公开(公告)号：GB2571825A

    公开(公告)日：2019-09-11

    申请号：GB201900596

    申请日：2019-01-16

    Applicant: ADOBE INC

    Inventor： ZHE LIN ,  YUFEI WANG ,  XIAOHUI SHEN ,  SCOTT D COHEN ,  JIANMING ZHANG

    IPC: G06K9/62 ,  G06K9/00 ,  G06T7/10

    Abstract: Computer-implemented segmentation techniques are disclosed for identifying features in an image based on text tags. The method comprises: converting a tag 118 into a vector representation 202, the tag defining a semantic class 120 to be located in a digital image 106; generating an attention map 210 by an embedding neural network 208 based on the digital image and the vector representation, the attention map defining a location in the digital image that corresponds to the semantic class, where the embedding neural network has been trained using image-level tags of respective semantic classes; refining 212 the location of the semantic class in the attention map by a refinement neural network 214 , the refinement neural network trained using localized tags of respective semantic classes; and indicating the refined location of the semantic class in the digital image using the refined attention map 216. The method thus makes use of tags for similar items in a machine learning environment in order to provide more examples for training.

    Learning parameters for neural networks using a semantic discriminator and an object-level discriminator
    5.
    发明专利
    Learning parameters for neural networks using a semantic discriminator and an object-level discriminator 未知

    公开(公告)号：GB2623162B

    公开(公告)日：2025-01-01

    申请号：GB202311936

    申请日：2023-08-03

    Applicant: ADOBE INC

    Inventor： ZHE LIN ,  HAITIAN ZHENG ,  ELYA SHECHTMAN ,  JIANMING ZHANG ,  JINGWAN LU ,  NING XU ,  QING LIU ,  SCOTT COHEN ,  SOHRAB AMIRGHODSI

    IPC: G06T5/60 ,  G06T5/77

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for panoptically guiding digital image inpainting utilizing a panoptic inpainting neural network. In some embodiments, the disclosed systems utilize a panoptic inpainting neural network to generate an inpainted digital image according to panoptic segmentation map that defines pixel regions corresponding to different panoptic labels. In some cases, the disclosed systems train a neural network utilizing a semantic discriminator that facilitates generation of digital images that are realistic while also conforming to a semantic segmentation. The disclosed systems generate and provide a panoptic inpainting interface to facilitate user interaction for inpainting digital images. In certain embodiments, the disclosed systems iteratively update an inpainted digital image based on changes to a panoptic segmentation map.

    Object detection in images
    6.
    发明专利
    Object detection in images 未知

    公开(公告)号：GB2578950B

    公开(公告)日：2021-03-10

    申请号：GB201912054

    申请日：2019-08-22

    Applicant: ADOBE INC

    Inventor： ZHE LIN ,  XIAOHUI SHEN ,  MINGYANG LING ,  JIANMING ZHANG ,  JASON KUEN

    IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04

    Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.

    Utilizing a neural network having a two-stream encoder architecture to generate composite digital images
    8.
    发明专利
    Utilizing a neural network having a two-stream encoder architecture to generate composite digital images 未知

    公开(公告)号：GB2587841B

    公开(公告)日：2022-09-21

    申请号：GB202007986

    申请日：2020-05-28

    Applicant: ADOBE INC

    Inventor： ZHE LIN ,  JIANMING ZHANG ,  HE ZHANG ,  FEDERICO PERAZZI

    IPC: G06T11/60 ,  G06T7/194

    Abstract: The present disclosure relates to utilizing a neural network having a two-stream encoder architecture to accurately generate composite digital images that realistically portray a foreground object from one digital image against a scene from another digital image. For example, the disclosed systems can utilize a foreground encoder of the neural network to identify features from a foreground image and further utilize a background encoder to identify features from a background image. The disclosed systems can then utilize a decoder to fuse the features together and generate a composite digital image. The disclosed systems can train the neural network utilizing an easy-to-hard data augmentation scheme implemented via self-teaching. The disclosed systems can further incorporate the neural network within an end-to-end framework for automation of the image composition process.

    Object detection in images
    9.
    发明专利
    Object detection in images 未知

    公开(公告)号：GB2578950A

    公开(公告)日：2020-06-03

    申请号：GB201912054

    申请日：2019-08-22

    Applicant: ADOBE INC

    Inventor： ZHE LIN ,  XIAOHUI SHEN ,  MINGYANG LING ,  JIANMING ZHANG ,  JASON KUEN

    IPC: G06K9/00 ,  G06K9/62

    Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network 202 to determine an attention map 208 of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word-embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via cite conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded without the need to scale training databases to include additional classes.

    Image and object inpainting with diffusion models
    10.
    发明专利
    Image and object inpainting with diffusion models 未知

    公开(公告)号：GB2624754B

    公开(公告)日：2025-02-05

    申请号：GB202314582

    申请日：2023-09-22

    Applicant: ADOBE INC

    Inventor： HAITIAN ZHENG ,  ZHE LIN ,  CONNELLY STUART BARNES ,  ELYA SHECHTMAN ,  JINGWAN LU ,  QING LIU ,  SOHRAB AMIRGHODSI ,  YUQIAN ZHOU ,  SCOTT COHEN ,  JIANMING ZHANG

    IPC: G06T5/77

    Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image comprising a first region that includes content and a second region to be inpainted. Noise is then added to the image to obtain a noisy image, and a plurality of intermediate output images are generated based on the noisy image using a diffusion model trained using a perceptual loss. The intermediate output images predict a final output image based on a corresponding intermediate noise level of the diffusion model. The diffusion model then generates the final output image based on the intermediate output image. The final output image includes inpainted content in the second region that is consistent with the content in the first region.

Patent Agency Ranking