中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.013 seconds)

    Methods and Systems for Training Quantized Neural Radiance Field
    1.
    发明公开
    Methods and Systems for Training Quantized Neural Radiance Field 审中-公开

    公开(公告)号：US20240013479A1

    公开(公告)日：2024-01-11

    申请号：US18369904

    申请日：2023-09-19

    Applicant: SHANGHAITECH UNIVERSITY

    Inventor： Minye WU ,  Chaolin RAO ,  Xin LOU ,  Pingqiang ZHOU ,  Jingyi YU

    IPC: G06T15/55 ,  G06T15/20 ,  G06T17/20

    CPC classification number: G06T15/55 ,  G06T15/20 ,  G06T17/20 ,  G06T2210/56

    Abstract: A computer-implemented method includes encoding a radiance field of an object onto a machine learning model; conducting, based on a set of training images of the object, a training process on the machine learning model to obtain a trained machine learning model, wherein the training process includes a first training process using a plurality of first test sample points followed by a second training process using a plurality of second test sample points located within a threshold distance from a surface region of the object; obtaining target view parameters indicating a view direction of the object; obtaining a plurality of rays associated with a target image of the object; obtaining render sample points on the plurality of rays associated with the target image; and rendering, by inputting the render sample points to the trained machine learning model, colors associated with the pixels of the target image.

    CALIBRATION METHOD AND APPARATUS FOR PANORAMIC STEREO VIDEO SYSTEM
    2.
    发明申请
    CALIBRATION METHOD AND APPARATUS FOR PANORAMIC STEREO VIDEO SYSTEM 审中-公开

    公开(公告)号：US20190028693A1

    公开(公告)日：2019-01-24

    申请号：US16069181

    申请日：2016-01-12

    Applicant: SHANGHAITECH UNIVERSITY

    Inventor： Jingyi YU ,  Yi MA

    IPC: H04N13/246 ,  H04N13/282 ,  H04N13/239 ,  H04N13/243 ,  G06T7/73 ,  G06T7/80 ,  G06T7/33

    Abstract: A method of calibrating a camera array comprising a plurality of cameras configured to capture a plurality of images to generate a panorama, wherein the relative positions among the plurality of cameras are constant, the method comprising: moving the camera array from a first position to a second position; measuring a homogeneous transformation matrix of a reference point on the camera array between the first position and the second position; capturing images at the first position and the second position by a first camera and a second camera on the camera array; and determining a homogenous transformation matrix between the first camera and the second camera based on the images captured by the first camera and the second camera at the first position and the second position. The method further comprises identifying a feature in the images taken by the first camera at the first position and the second position, and estimating a rotation of the first camera from the first position to the second position based on the feature.

    Mixed-precision Neural Network Systems
    3.
    发明公开
    Mixed-precision Neural Network Systems 审中-公开

    公开(公告)号：US20240296308A1

    公开(公告)日：2024-09-05

    申请号：US18646852

    申请日：2024-04-26

    Applicant: SHANGHAITECH UNIVERSITY

    Inventor： Yueyang ZHENG ,  Chaolin RAO ,  Minye WU ,  Xin LOU ,  Pingqiang ZHOU ,  Jingyi YU

    IPC: G06N3/04

    CPC classification number: G06N3/04

    Abstract: A computing system for encoding a machine learning model comprises a plurality of layers and a plurality of computation units. A first set of computation units are configured to process data at a first bit width. A second set of computation units are configured to process at a second bit width. The first bit width is higher than the second bit width. A memory is coupled to the computation units. A controller is coupled to the computation units and the memory. The controller is configured to provide instructions for encoding the machine learning model. The first set of computation units are configured to compute a first set of layers and the second set of computation units are configured to compute a second set of layers.

    METHOD AND SYSTEM FOR THREE-DIMENSIONAL MODEL RECONSTRUCTION
    5.
    发明申请
    METHOD AND SYSTEM FOR THREE-DIMENSIONAL MODEL RECONSTRUCTION 审中-公开

    公开(公告)号：US20200074658A1

    公开(公告)日：2020-03-05

    申请号：US16675617

    申请日：2019-11-06

    Applicant: Shanghaitech University

    Inventor： Jingyi YU

    IPC: G06T7/557 ,  G06T17/00 ,  G06T15/20 ,  G06T7/73

    Abstract: A method of generating a three-dimensional model of an object is disclosed. The method may use a light field camera to capture a plurality of light field images at a plurality of viewpoints. The method may include capturing a first light field image at a first viewpoint; capturing a second light field image at the second viewpoint; estimating a rotation and a translation of a light field from the first viewpoint to the second viewpoint; obtaining a disparity map from each of the plurality of light field image; and computing a three-dimensional point cloud by optimizing the rotation and translation of the light field and the disparity map. The first light field image may include a first plurality of subaperture images and the second light field image may include a second plurality of subaperture images.

    SYSTEMS AND METHODS FOR ELECTRON CRYOTOMOGRAPHY RECONSTRUCTION
    6.
    发明申请
    SYSTEMS AND METHODS FOR ELECTRON CRYOTOMOGRAPHY RECONSTRUCTION 有权

    公开(公告)号：US20240412377A1

    公开(公告)日：2024-12-12

    申请号：US18542803

    申请日：2023-12-18

    Applicant: SHANGHAITECH UNIVERSITY

    Inventor： Peihao WANG ,  Jiakai ZHANG ,  Xinhang LIU ,  Zhijie LIU ,  Jingyi YU

    IPC: G06T7/149 ,  G06T9/00 ,  G06T15/10

    Abstract: Described herein are methods and non-transitory computer-readable media of a computing system configured to obtain a plurality of images of an object from a plurality of orientations at a plurality of times. A machine learning model is encoded to represent a continuous density field of the object that maps a spatial coordinate to a density value. The machine learning model comprises a deformation module configured to deform the spatial coordinate in accordance with a timestamp and a trained deformation weight. The machine learning model further comprises a neural radiance module configured to derive the density value in accordance with the deformed spatial coordinate, the timestamp, a direction, and a trained radiance weight. The machine learning model is trained using the plurality of images. A three-dimensional structure of the object is constructed based on the trained machine learning model.

    Multi-core Acceleration of Neural Rendering
    7.
    发明公开
    Multi-core Acceleration of Neural Rendering 审中-公开

    公开(公告)号：US20240281256A1

    公开(公告)日：2024-08-22

    申请号：US18646818

    申请日：2024-04-26

    Applicant: SHANGHAITECH UNIVERSITY

    Inventor： Yuhan GU ,  Chaolin RAO ,  Minye WU ,  Xin LOU ,  Pingqiang ZHOU ,  Jingyi YU

    IPC: G06F9/38 ,  G06T1/20 ,  G06T15/00

    CPC classification number: G06F9/3885 ,  G06T1/20 ,  G06T15/005

    Abstract: A computing core for rendering an image computing core comprises a position encoding logic and a plurality of pipeline logics connected in series in a pipeline. The position encoding logic is configured to transform coordinates and directions of sampling points corresponding to a portion of the image into high dimensional representations. The plurality of pipeline logics are configured to output, based on the high dimensional representation of the coordinates and the high dimensional representation of the directions, intensity and color values of pixels corresponding to the portion of the image in one pipeline cycle. The plurality of pipeline logics are configured to run in parallel.

Patent Agency Ranking