检索结果-南通市图书馆

Research on facial Expression Capture Based on Two-Stage Neural Network

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 4709-4725页

作者： Zhenzhou Wang Shao Cui Xiang Wang JiaFeng Tian School of Information Science and Engineering Hebei University of Science and TechnologyShijiazhuang050000China School of Engineering Newcastle UniversityNewcastle Upon TyneNE98United Kingdom

To generate realistic three-dimensional animation of virtual character,capturing real facial expression is the primary *** to diverse facial expressions and complex background,facial landmarks recognized by existing strategies have the problem of deviations and low ***,a method for facial expression capture based on two-stage neural network is proposed in this paper which takes advantage of improved multi-task cascaded convolutional networks(MTCNN)and high-resolution ***,the convolution operation of traditional MTCNN is *** face information in the input image is quickly filtered by feature fusion in the first stage and Octave Convolution instead of the original ones is introduced into in the second stage to enhance the feature extraction ability of the network,which further rejects a large number of false *** model outputs more accurate facial candidate windows for better landmarks recognition and locates the *** the images cropped after face detection are input into high-resolution ***-scale feature fusion is realized by parallel connection of multi-resolution streams,and rich high-resolution heatmaps of facial landmarks are ***,the changes of facial landmarks recognized are tracked in *** expression parameters are extracted and transmitted to Unity3D engine to drive the virtual character’s face,which can realize facial expression synchronous *** experimental results obtained on the WFLW database demonstrate the superiority of the proposed method in terms of accuracy and robustness,especially for diverse expressions and complex *** method can accurately capture facial expression and generate three-dimensional animation effects,making online entertainment and social interaction more immersive in shared virtual space.

关键词： facial expression capture facial landmarks multi-task cascaded convolutional networks high-resolution network animation generation

Joint head pose and facial landmark regression from depth images

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2017年第3期3卷 229-241页

作者： Jie Wang Juyong Zhang Changwei Luo Falai Chen University of Science and Technology of China HefeiAnhui230026China.

This paper presents a joint head pose and facial landmark regression method with input from depth images for realtime application. Our main contributions are: firstly, a joint optimization method to estimate head pose and facial landmarks, i.e., the pose regression result provides supervised initialization for cascaded facial landmark regression, while the regression result for the facial landmarks can also help to further refine the head pose at each stage. Secondly,we classify the head pose space into 9 sub-spaces, and then use a cascaded random forest with a global shape constraint for training facial landmarks in each specific space. This classification-guided method can effectively handle the problem of large pose changes and ***, we have built a 3D face database containing 73 subjects, each with 14 expressions in various head poses. Experiments on challenging databases show our method achieves state-of-the-art performance on both head pose estimation and facial landmark regression.

关键词： head pose facial landmarks depth images

facial landmark disentangled network with variational autoencoder

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics(A Journal of Chinese Universities) 2022年第2期37卷 290-305页

作者： LIANG Sen ZHOU Zhi-ze GUO Yu-dong GAO Xuan ZHANG Ju-yong BAO Hu-jun CAD&CG State Labs Zhejiang UniversityHangzhou 310027China School of Mathematical Sciences University of Science and Technology of ChinaHefei 230026China.

Learning disentangled representation of data is a key problem in deep ***,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of face reconstruction,face reenactment and talking head et al..However,due to the sparsity of landmarks and the lack of accurate labels for the factors,it is hard to learn the disentangled representation of *** address these problem,we propose a simple and effective model named FLD-VAE to disentangle arbitrary facial landmarks into identity and expression latent representations,which is based on a Variational Autoencoder ***,we propose three invariant loss functions in both latent and data levels to constrain the invariance of representations during training ***,we implement an identity preservation loss to further enhance the representation ability of identity *** the best of our knowledge,this is the first work to end-to-end disentangle identity and expression factors simultaneously from one single facial landmark.

关键词： disentanglement representation deep learning facial landmarks variational autoencoder

facial Landmark Localization by Gibbs Sampling

在线全文

学校读者我要写书评

暂无评论

ZTE Communications 2014年第4期12卷 23-29页

作者： Bofei Wang Diankai Zhang Chi Zhang Jiani Hu Weihong Deng ZTE Corporation Beijing University of Posts and Telecommunication

In this paper, we introduce a novel method for facial landmark detection. We localize facial landmarks according to the MAP crite rion. Conventional gradient ascent algorithms get stuck at the local optimal solution. Gibbs sampling is a kind of Markov Chain Monte Carlo （MCMC） algorithm. We choose it for optimization because it is easy to implement and it guarantees global conver gence. The posterior distribution is obtained by learning prior distribution and likelihood function. Prior distribution is assumed Gaussian. We use Principle Component Analysis （PCA） to reduce the dimensionality and learn the prior distribution. Local Linear Support Vector Machine （LLSVM） is used to get the likelihood function of every key point. In our experiment, we compare our de tector with some other wellknown methods. The results show that the proposed method is very simple and efficient. It can avoid trapping in local optimal solution.

关键词： facial landmarks MAP Gibbs sampling MCMC LL-SVM