中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.014 seconds)

    AUDIO-SPEECH DRIVEN ANIMATED TALKING FACE GENERATION USING A CASCADED GENERATIVE ADVERSARIAL NETWORK
    1.
    发明申请
    AUDIO-SPEECH DRIVEN ANIMATED TALKING FACE GENERATION USING A CASCADED GENERATIVE ADVERSARIAL NETWORK 有权

    公开(公告)号：US20220036617A1

    公开(公告)日：2022-02-03

    申请号：US17199149

    申请日：2021-03-11

    Applicant: Tata Consultancy Services Limited

    Inventor： Sandika BISWAS ,  Dipanjan DAS ,  Sanjana SINHA ,  Brojeshwar BHOWMICK

    IPC: G06T13/20 ,  G10L15/02 ,  G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

    Abstract: Conventional state-of-the-art methods are limited in their ability to generate realistic animation from audio on any unknown faces and cannot be easily generalized to different facial characteristics and voice accents. Further, these methods fail to produce realistic facial animation for subjects which are quite different than that of distribution of facial characteristics network has seen during training. Embodiments of the present disclosure provide systems and methods that generate audio-speech driven animated talking face using a cascaded generative adversarial network (CGAN), wherein a first GAN is used to transfer lip motion from canonical face to person-specific face. A second GAN based texture generator network is conditioned on person-specific landmark to generate high-fidelity face corresponding to the motion. Texture generator GAN is made more flexible using meta learning to adapt to unknown subject's traits and orientation of face during inference. Finally, eye-blinks are induced in the final animation face being generated.

    METHOD AND SYSTEM FOR AGRICULTURE FIELD CLUSTERING AND ECOLOGICAL FORECASTING
    2.
    发明申请
    METHOD AND SYSTEM FOR AGRICULTURE FIELD CLUSTERING AND ECOLOGICAL FORECASTING 审中-公开

    公开(公告)号：US20170223900A1

    公开(公告)日：2017-08-10

    申请号：US15213831

    申请日：2016-07-19

    Applicant: Tata Consultancy Services Limited

    Inventor： Bhushan JAGYASI ,  Sandika BISWAS ,  Jayantrao MOHITE

    IPC: A01G1/00 ,  A01G7/00 ,  G06N5/04

    Abstract: A method and system is provided for agriculture field clustering and ecological forecasting. The present application provides a method and system for agriculture field clustering and ecological forecasting based on the clustered agriculture fields, comprises capturing an absolute ground data representing a plurality of field measurements of the agriculture fields; capturing a plurality of weather conditions of the agriculture fields; generating a feature set comprising of said absolute ground data and weather data of the agriculture fields; adaptively clustering the plurality of agriculture fields based on the feature set to generate a cluster; generating a generic forecasting model for ecological forecasting comprising of common features of the feature set in said cluster; selecting at least one feature out of the feature set for generating a plurality of adaptive forecasting model based for ecological forecasting and recommending control measures to a user.

    IDENTITY PRESERVING REALISTIC TALKING FACE GENERATION USING AUDIO SPEECH OF A USER
    4.
    发明申请
    IDENTITY PRESERVING REALISTIC TALKING FACE GENERATION USING AUDIO SPEECH OF A USER 有权

    公开(公告)号：US20210366173A1

    公开(公告)日：2021-11-25

    申请号：US17036583

    申请日：2020-09-29

    Applicant: Tata Consultancy Services Limited

    Inventor： Sanjana SINHA ,  Sandika BISWAS ,  Brojeshwar BHOWMICK

    IPC: G06T13/20 ,  G10L15/02 ,  G06T13/40 ,  G06K9/00 ,  G06K9/62

    Abstract: Speech-driven facial animation is useful for a variety of applications such as telepresence, chatbots, etc. The necessary attributes of having a realistic face animation are: 1) audiovisual synchronization, (2) identity preservation of the target individual, (3) plausible mouth movements, and (4) presence of natural eye blinks. Existing methods mostly address audio-visual lip synchronization, and synthesis of natural facial gestures for overall video realism. However, existing approaches are not accurate. Present disclosure provides system and method that learn motion of facial landmarks as an intermediate step before generating texture. Person-independent facial landmarks are generated from audio for invariance to different voices, accents, etc. Eye blinks are imposed on facial landmarks and the person-independent landmarks are retargeted to person-specific landmarks to preserve identity related facial structure. Facial texture is then generated from person-specific facial landmarks that helps to preserve identity-related texture.

    WEAKLY SUPERVISED LEARNING OF 3D HUMAN POSES FROM 2D POSES
    5.
    发明申请
    WEAKLY SUPERVISED LEARNING OF 3D HUMAN POSES FROM 2D POSES 审中-公开

    公开(公告)号：US20200342270A1

    公开(公告)日：2020-10-29

    申请号：US16815206

    申请日：2020-03-11

    Applicant: Tata Consultancy Services Limited

    Inventor： Sandika BISWAS ,  Sanjana SINHA ,  Kavya GUPTA ,  Brojeshwar BHOWMICK

    IPC: G06K9/62 ,  G06K9/00 ,  G06N3/08

    Abstract: Estimating 3D human pose from monocular images is a challenging problem due to the variety and complexity of human poses and the inherent ambiguity in recovering depth from single view. Recent deep learning based methods show promising results by using supervised learning on 3D pose annotated datasets. However, the lack of large-scale 3D annotated training data makes the 3D pose estimation difficult in-the-wild. Embodiments of the present disclosure provide a method which can effectively predict 3D human poses from only 2D pose in a weakly-supervised manner by using both ground-truth 3D pose and ground-truth 2D pose based on re-projection error minimization as a constraint to predict the 3D joint locations. The method may further utilize additional geometric constraints on reconstructed body parts to regularize the pose in 3D along with minimizing re-projection error to improvise on estimating an accurate 3D pose.

Patent Agency Ranking