专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明专利

GB2581374B 3D face reconstruction system and method 未知
公开(公告)号：GB2581374B
公开(公告)日：2022-05-11
申请号：GB201902067
申请日：2019-02-14
申请人： HUAWEI TECH CO LTD
发明人： BARIS GECER , STEFANOS ZAFEIRIOU
IPC分类号： G06T15/20 , G06T15/04 , G06T17/20 , G06V10/74 , G06V10/75 , G06V40/16
摘要： A computer implemented method 500 for generating a 3D facial reconstruction based on an input facial image is presented. The method comprises generating an initial reconstruction 510 and iteratively updating 520 the reconstruction. The initial reconstruction is generated by generating 512 a facial mesh, using a shape model, and a texture map 514. The reconstruction is iteratively updated by using a differentiable renderer to project 522 the 3D reconstruction onto a 2D plane to form a rendered facial image, calculating 524 a loss function based on a comparison of the rendered facial image and the input facial image, and using gradient descent to generate 526 an updated facial reconstruction. The facial mesh may use an expression model (figure 1, 102) and the projection may be affected by illumination (figure 1, 103) and camera (figure 1, 104) parameters. The generation of the reconstruction may comprise the use of a generative adversarial network (GAN). The loss function calculation may use a comparison of the presence and/or position of facial landmarks between the input and rendered images. The loss function calculation may use the pixel-to-pixel dissimilarity (figure 3, 320) between the images. There may be more than one input image.

12. 发明专利

GB2582833B Facial localisation in images 未知
公开(公告)号：GB2582833B
公开(公告)日：2021-04-07
申请号：GB201906027
申请日：2019-04-30
申请人： HUAWEI TECH CO LTD
发明人： JIANKANG DENG , STEFANOS ZAFEIRIOU
IPC分类号： G06K9/00 , G06N3/04 , G06N3/08
摘要： The invention relates to methods of facial localisation in images. According to a first aspect (Fig. 2), there is described a computer-implemented method of training a neural network 106 for face localisation, the method comprising: inputting, to the neural network, a training image 202 comprising one or more faces (104); processing, using the neural network, the training image and outputting for each of a plurality of training anchors in the training image, one or more sets of output data, wherein the output data comprises a predicted facial classification, a predicted location of a corresponding face box (110), and one or more corresponding feature vectors; then updating parameters of the neural network in dependence on an objective function. The objective function comprises, for each positive anchor in the training image, a classification loss 210, a box regression loss 212 and a feature loss 214, based on comparisons of predicted properties with known properties in the anchor. A second aspect (Fig. 1) covers using a neural network to perform face localisation, wherein the network comprises convolutional layers and filters, as well as skip connections.

13. 发明专利

GB2592076B Method of training an image classification model 未知
公开(公告)号：GB2592076B
公开(公告)日：2022-09-07
申请号：GB202002157
申请日：2020-02-17
申请人： HUAWEI TECH CO LTD
发明人： JIANKANG DENG , STEFANOS ZAFEIRIOU
IPC分类号： G06V10/77 , G06K9/62 , G06N3/08
摘要： Method of training a neural network classifier, comprising: extracting from the neural network 204 a plurality of subclass centre vectors 210; generating an embedding vector 206 from an input image 202; determining a similarity score 212 between the embedding vector and each of the subclass centre vectors; updating neural network parameters 214 in dependence each of the similarity scores using an objective function; and extracting and updating each subclass centre vector from the neural network. Subclass centre vectors may be extracted from the neural network’s last fully connected layer. The objective function may comprise a multi-centre loss term such as a margin-based Softmax loss function, that determines, for the embedding vector, a closest subclass centre vector for each class using the similarity scores. The embedding vector and subclass centre vectors may be normalised, and the similarity score an angle therebetween. The objective function may comprise an intra-class compactness term that uses the intra-class normalized angle similarity score between sub-class a dominant vector and the other sub-classes. Non-dominant subclasses may be discarded after a number of training cycles have been run. The method may be used to train a neural network on face images that contain noise (wrong labels).

14. 发明专利

GB2581991B Enhancement of three-dimensional facial scans 未知
公开(公告)号：GB2581991B
公开(公告)日：2022-06-01
申请号：GB201903017
申请日：2019-03-06
申请人： HUAWEI TECH CO LTD
发明人： STYLIANOS MOSCHOGLOU , STYLIANOS PLOUMPIS , STEFANOS ZAFEIRIOU
IPC分类号： G06T5/00 , G06N3/08 , G06T1/40
摘要： A method includes applying a generator neural network to a low quality spatial UV map to generate a candidate high quality spatial UV map, applying a discriminator neural network to the candidate high quality spatial UV map to generate a reconstructed candidate high quality spatial UV map, applying the discriminator neural network to a high quality ground truth spatial UV map to generate a reconstructed high quality ground truth spatial UV map, updating parameters of the generator neural network based on a comparison of the candidate high quality spatial UV map and the reconstructed candidate high quality spatial UV map, and updating parameters of the discriminator neural network.

15. 发明专利

GB2588747B Facial behaviour analysis 未知
公开(公告)号：GB2588747B
公开(公告)日：2021-12-08
申请号：GB201909300
申请日：2019-06-28
申请人： HUAWEI TECH CO LTD
发明人： STEFANOS ZAFEIRIOU , DIMITRIOS KOLLIAS
IPC分类号： G06K9/62 , G06K9/00 , G06N3/02
摘要： This invention relates to methods for analysing facial behaviour in facial images using neural networks (NN). A first aspect covers a method of training a NN 212, the method comprising: inputting to the NN a plurality of facial images, the images comprising: one or more images from a first dataset 202-1 wherein each image comprises a known emotion label 204 (e.g. happy, sad); and one or more images from a second dataset 201-2 wherein each image comprises a known action unit activation 206 (e.g. wrinkled nose, raised eyebrow). The method further comprises: generating for each of the images using the NN, a predicted emotion label 214 and predicted action unit activation 216; then updating parameters of the NN in dependence on a comparison of the predicted and known emotion labels, and the predicted and known action unit activations. The comparison could be performed using a multi-task function 222-226 for calculating losses, e.g. cross entropy loss. Further images 202-3 having known arousal or valence values 208 could also be used. A second aspect covers using the trained NN to classify facial images.

16. 发明专利

GB2582047B Combining three-dimensional morphable models 未知
公开(公告)号：GB2582047B
公开(公告)日：2021-03-31
申请号：GB201917826
申请日：2019-03-08
申请人： HUAWEI TECH CO LTD
发明人： STYLIANOS PLOUMPIS , STEFANOS ZAFEIRIOU
IPC分类号： G06T19/20
摘要： A Gaussian process morphable model (GPMM) is generated by combining first and second 3DMMs (see fig. 4) by registering a mean shape of the first 3DMM to a mean shape of the second 3DMM and a template shape, and projecting template shape points onto the mean shapes of the first and/or second 3DMM. A universal covariance matrix for the GPMM is determined based on pairs of template shape points projected onto the mean shape of the first and/or second 3DMM, and a covariance matrix for each of the first and second 3DMMs. The GPMM is defined based on the universal covariance matrix and a predefined mean deformation. Also disclosed is producing a three-dimensional morphable model, (3DMM) by combining first and second 3DMMs, by generating (2.1) a plurality of first shapes using the first 3DMM, and calculating (2.2) a mapping from second parameters of the second 3DMM to first parameters of the first 3DMM. For each second shape generated using the second 3DMM, a corresponding first shape is generated (2.3). Merged shapes are formed (2.4) by merging each second shape with the corresponding first shape. Principal component analysis is performed (2.5) on the merged shapes to generate the new 3DMM.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式