中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

32 records (took 0.014 seconds)

    Image upscaling
    12.
    发明授权
    Image upscaling 有权

    公开(公告)号：US09996902B2

    公开(公告)日：2018-06-12

    申请号：US15000670

    申请日：2016-01-19

    Applicant: Google LLC

    Inventor： Peyman Milanfar ,  Yaniv Romano

    IPC: G06T3/40 ,  G06K9/46 ,  G06T5/00 ,  G06T5/50

    CPC classification number: G06T3/4053 ,  G06K9/4604 ,  G06T3/40 ,  G06T3/403 ,  G06T5/003 ,  G06T5/50 ,  G06T2207/20024 ,  G06T2207/20081 ,  G06T2207/20221 ,  G06T2210/36

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for upscaling an image. One of the methods includes upscaling a low resolution image, creating first pixel subsets of the first upscaled image, creating second pixel subsets of a high resolution image, determining, for each subset in the pixel subsets, a value of a property of the pixel subset, determining, for each subset in the pixel subsets, a group of subsets to which the corresponding pixel subset belongs using the value of the property, and determining, for each of the groups of subsets, a filter to apply to each of the first pixel subsets that correspond to the pixel subsets in the group to create a final pixel subset that approximates the corresponding second pixel subset using the first pixel subset, a combination of all of the final pixel subsets representing a second upscaled image.

    Multi-scale Transformer for Image Analysis
    13.
    发明申请
    Multi-scale Transformer for Image Analysis 有权

    公开(公告)号：US20250124537A1

    公开(公告)日：2025-04-17

    申请号：US18999336

    申请日：2024-12-23

    Applicant: Google LLC

    Inventor： Junjie Ke ,  Feng Yang ,  Qifei Wang ,  Yilin Wang ,  Peyman Milanfar

    IPC: G06T3/04 ,  G06T3/40 ,  G06T7/00

    Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

    MULTILAYER LAPLACIAN RESIZER FOR COMPUTER VISION SYSTEMS
    14.
    发明公开
    MULTILAYER LAPLACIAN RESIZER FOR COMPUTER VISION SYSTEMS 审中-公开

    公开(公告)号：US20240331091A1

    公开(公告)日：2024-10-03

    申请号：US18621434

    申请日：2024-03-29

    Applicant: Google LLC

    Inventor： Hossein Talebi ,  Zhengzhong Tu ,  Peyman Milanfar

    IPC: G06T5/20 ,  G06T5/50

    CPC classification number: G06T5/20 ,  G06T5/50 ,  G06T2207/20024 ,  G06T2207/20212

    Abstract: The technology provides an image resizer that is jointly trainable with neural network classification (recognition) models, and is designed to improve classification performance. Systems and method include applying an input image to a baseline resizer to obtain a default resized image, and applying the input image to a plurality of filters. Each respective filter in the plurality is configured to perform sub-band filtering on the input image to obtain a sub-band filtered result. This includes applying the sub-band filtered result to the baseline resizer to obtain a respective resized result, and also includes applying to the respective resized result a scaling parameter, a bias parameter, and a nonlinear function to obtain a respective filtered image. The process then combines the default resized image and the respective filtered images to generate a combined resized image.

    METHODS, SYSTEMS, AND MEDIA FOR DETERMINING PERCEPTUAL QUALITY INDICATORS OF VIDEO CONTENT ITEMS
    15.
    发明公开
    METHODS, SYSTEMS, AND MEDIA FOR DETERMINING PERCEPTUAL QUALITY INDICATORS OF VIDEO CONTENT ITEMS 审中-公开

    公开(公告)号：US20230319327A1

    公开(公告)日：2023-10-05

    申请号：US18021636

    申请日：2022-06-08

    Applicant: Google LLC

    Inventor： Yilin Wang ,  Balineedu Adsumilli ,  Junjie Ke ,  Hossein Talebi ,  Joong Yim ,  Neil Birkbeck ,  Peyman Milanfar ,  Feng Yang

    IPC: H04N21/234 ,  H04N19/154 ,  H04N21/466

    CPC classification number: H04N21/23418 ,  H04N19/154 ,  H04N21/4668

    Abstract: Methods, systems, and media for determining perceptual quality indicators of video content items are provided. In some embodiments, the method comprises: receiving a video content item; extracting a plurality of frames from the video content item; determining, using a first subnetwork of a deep neural network, a content quality indicator for each frame of the plurality of frames of the video content item; determining, using a second subnetwork of the deep neural network, a video distortion indicator for each frame of the plurality of frames of the video content item; determining, using a third subnetwork of the deep neural network, a compression sensitivity indicator for each frame of the plurality of frames of the video content item; generating a quality level for each frame of the plurality of frames of the video content item that concatenates the content quality indicator, the video distortion indicator, and the compression sensitivity indicator for that frame of the video content item; generating an overall quality level for video content item by aggregating the quality level of each frame of the plurality of frames; and causing a video recommendation to be presented based on the overall quality level of the video content item.

    Multi-scale transformer for image analysis
    18.
    发明授权
    Multi-scale transformer for image analysis 有权

    公开(公告)号：US12217382B2

    公开(公告)日：2025-02-04

    申请号：US18527528

    申请日：2023-12-04

    Applicant: Google LLC

    Inventor： Junjie Ke ,  Feng Yang ,  Qifei Wang ,  Yilin Wang ,  Peyman Milanfar

    IPC: G06K9/00 ,  G06T3/04 ,  G06T3/40 ,  G06T7/00

    Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.

    Multi-Axis Vision Transformer
    19.
    发明申请
    Multi-Axis Vision Transformer 有权

    公开(公告)号：US20250022269A1

    公开(公告)日：2025-01-16

    申请号：US18902546

    申请日：2024-09-30

    Applicant: Google LLC

    Inventor： Yinxiao Li ,  Feng Yang ,  Peyman Milanfar ,  Han Zhang ,  Zhengzhong Tu ,  Hossein Talebi

    IPC: G06V10/82 ,  G06V10/77

    Abstract: Provided is an efficient and scalable attention model that can be referred to as multi-axis attention. Example implementations can include two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions with only linear complexity. The present disclosure also presents a new architectural element by effectively blending the proposed multi-axis attention model with convolutions. In addition, the present disclosure proposes a simple hierarchical vision backbone, example implementations of which can be referred to as MaxViT, by simply repeating the basic building block over multiple stages. Notably, MaxViT is able to “see” globally throughout the entire network, even in earlier, high-resolution stages.

Patent Agency Ranking