专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

GB2594970A Three-dimensional motion estimation 未知
公开(公告)号：GB2594970A
公开(公告)日：2021-11-17
申请号：GB202007065
申请日：2020-05-13
申请人： HUAWEI TECH CO LTD
发明人： RAMI KOUJAN , ANASTASIOS ROUSSOS , STEFANOS ZAFEIROU
IPC分类号： G06T7/269
摘要： The specification relates to methods and systems for estimating three-dimensional motion flow between two-dimensional images, in particular to estimating the three-dimensional motion flow of an object, such as a face, between two-dimensional images. This specification describes a computer implemented method of estimating a three-dimensional flow of an object between a first two-dimensional image comprising an image of the object in a first configuration and a second two-dimensional image comprising an image of the object in a second configuration, the method comprises inputting the first image two-dimensional, the second image two-dimensional and a two-dimensional representation of an estimated three-dimensional shape of the object into a convolutional neural network and generating, using the convolutional neural network, the three-dimensional flow of the object between the first two-dimensional image and the second two-dimensional image from the first two-dimensional image, the second two-dimensional image and the two-dimensional representation of the estimated three-dimensional shape of the object.

2. 发明专利

GB2596777A Facial re-enactment 未知
公开(公告)号：GB2596777A
公开(公告)日：2022-01-12
申请号：GB202007052
申请日：2020-05-13
申请人： HUAWEI TECH CO LTD
发明人： STEFANOS ZAFEIRIOU , RAMI KOUJAN , MICHAIL-CHRISTOS DOUKAS
IPC分类号： G06T13/40 , G06K9/00
摘要： A first plurality of sequential source face coordinate images and gaze tracking images are generated based on a plurality of source input images of a first source subject or actor 12. The first plurality of source face coordinate images comprise source identity parameters and source expression parameters, wherein the source expression parameters are represented as offsets from the source identity parameters. A plurality of sequential target face coordinate images and gaze tracking images of the first target subject or actor 14 are generated based on a plurality of target input images of a first target subject. Using a first neural network, a plurality of sequential output images 16 are generated using a mapping module 10, wherein the plurality of sequential output images are based on a mapping of the source expression parameters and the source gaze tracking images on the target identity parameters. The neural network may be a generative adversarial network trained to generate the output images by inputting the source and target coordinate and gaze tracking images. A loss function may be used based on ground truth inputs and the sequential output images.

你已经成功收藏专利！

检索式保存成功!

IPRDB