中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

39 records (took 0.035 seconds)

    CAMERA AGNOSTIC DEPTH NETWORK
    11.
    发明申请
    CAMERA AGNOSTIC DEPTH NETWORK 有权

    公开(公告)号：US20210398301A1

    公开(公告)日：2021-12-23

    申请号：US16904444

    申请日：2020-06-17

    Applicant: TOYOTA RESEARCH INSTITUTE, INC.

    Inventor： Vitor GUIZILINI ,  Sudeep PILLAI ,  Adrien David GAIDON ,  Rares A. AMBRUS ,  Igor VASILJEVIC

    IPC: G06T7/50 ,  G06T7/70

    Abstract: A method for monocular depth/pose estimation in a camera agnostic network is described. The method includes training a monocular depth model and a monocular pose model to learn monocular depth estimation and monocular pose estimation based on a target image and context images from monocular video captured by the camera agnostic network. The method also includes lifting 3D points from image pixels of the target image according to the context images. The method further includes projecting the lifted 3D points onto an image plane according to a predicted ray vector based on the monocular depth model, the monocular pose model, and a camera center of the camera agnostic network. The method also includes predicting a warped target image from a predicted depth map of the monocular depth model, a ray surface of the predicted ray vector, and a projection of the lifted 3D points according to the camera agnostic network.

    SYSTEM AND METHOD FOR SELF-SUPERVISED MONOCULAR DEPTH REGULARIZATION FROM SURFACE NORMALS
    15.
    发明申请
    SYSTEM AND METHOD FOR SELF-SUPERVISED MONOCULAR DEPTH REGULARIZATION FROM SURFACE NORMALS 有权

    公开(公告)号：US20210407115A1

    公开(公告)日：2021-12-30

    申请号：US16913214

    申请日：2020-06-26

    Applicant: TOYOTA RESEARCH INSTITUTE, INC.

    Inventor： Vitor GUIZILINI ,  Adrien David GAIDON ,  Rares A. AMBRUS

    IPC: G06T7/50

    Abstract: Systems and methods for generating depth models and depth maps from images obtained from an imaging system are presented. A self-supervised neural network may be capable of regularizing depth information from surface normals. Rather than rely on separate depth and surface normal networks, surface normal information is extracted from the depth information and a smoothness function is applied to the surface normals instead of a depth gradient. Smoothing the surface normal may provide improved representation of environmental structures by both smoothing texture-less areas while preserving sharp boundaries between structures.

    MULTI-SCALE RECURRENT DECODER FOR MONOCULAR DEPTH ESTIMATION
    16.
    发明申请
    MULTI-SCALE RECURRENT DECODER FOR MONOCULAR DEPTH ESTIMATION 有权

    公开(公告)号：US20210390718A1

    公开(公告)日：2021-12-16

    申请号：US16899425

    申请日：2020-06-11

    Applicant: TOYOTA RESEARCH INSTITUTE, INC.

    Inventor： Vitor GUIZILINI ,  Adrien David GAIDON

    IPC: G06T7/50 ,  G06T3/40

    Abstract: A method for estimating depth is presented. The method includes generating, at each decoding layer of a neural network, decoded features of an input image. The method also includes upsampling, at each decoding layer, the decoded features to a resolution of a final output of the neural network. The method still further includes concatenating, at each decoding layer, the upsampled decoded features with features generated at a convolution layer of the neural network. The method additionally includes sequentially receiving the concatenated upsampled decoded features at a long-short term memory (LSTM) module of the neural network from each decoding layer. The method still further includes generating, at the LSTM module, a depth estimate of the input image after receiving the concatenated upsampled inverse depth estimate from a final layer of a decoder of the neural network. The method also includes controlling an action of an agent based on the depth estimate.

    DEPTH ESTIMATION BASED ON EGO-MOTION ESTIMATION AND RESIDUAL FLOW ESTIMATION
    17.
    发明申请
    DEPTH ESTIMATION BASED ON EGO-MOTION ESTIMATION AND RESIDUAL FLOW ESTIMATION 有权

    公开(公告)号：US20210319577A1

    公开(公告)日：2021-10-14

    申请号：US17230941

    申请日：2021-04-14

    Applicant: TOYOTA RESEARCH INSTITUTE, INC.

    Inventor： Jiexiong TANG ,  Rares Andrei AMBRUS ,  Vitor GUIZILINI ,  Adrien David GAIDON

    IPC: G06T7/55 ,  G06T7/70 ,  G06T3/00 ,  G06T3/40

    Abstract: A method for depth estimation performed by a depth estimation system of an autonomous agent includes determining a first pose of a sensor based on a first image captured by the sensor and a second image captured by the sensor. The method also includes determining a first depth of the first image and a second depth of the second image. The method further includes generating a warped depth image based on at least the first depth and the first pose. The method still further includes determining a second pose based on the warped depth image and the second depth image. The method also includes updating the first pose based on the second pose and updating a first warped image based on the updated first pose.

    SEMANTICALLY AWARE KEYPOINT MATCHING
    18.
    发明申请
    SEMANTICALLY AWARE KEYPOINT MATCHING 有权

    公开(公告)号：US20210319236A1

    公开(公告)日：2021-10-14

    申请号：US17230947

    申请日：2021-04-14

    Applicant: TOYOTA RESEARCH INSTITUTE, INC.

    Inventor： Jiexiong TANG ,  Rares Andrei AMBRUS ,  Vitor GUIZILINI ,  Adrien David GAIDON

    IPC: G06K9/00 ,  G06K9/62 ,  G05D1/02

    Abstract: A method for keypoint matching includes receiving an input image obtained by a sensor of an agent. The method also includes identifying a set of keypoints of the received image. The method further includes augmenting the descriptor of each of the keypoints with semantic information of the input image. The method also includes identifying a target image based on one or more semantically augmented descriptors of the target image matching one or more semantically augmented descriptors of the input image. The method further includes controlling an action of the agent in response to identifying the target.

Patent Agency Ranking