论文阅读 [TPAMI-2022] Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasse

论文阅读 [TPAMI-2022] Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets

论文搜索(studyai.com)

搜索论文: Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets

搜索论文: http://www.studyai.com/search/whole-site/?q=Dynamic+Facial+Expression+Generation+on+Hilbert+Hypersphere+With+Conditional+Wasserstein+Generative+Adversarial+Nets

关键字(Keywords)

Face; Gallium nitride; Generative adversarial networks; Videos; Dynamics; Geometry; Training; Facial expression generation; conditional manifold-valued wasserstein generative adversarial networks; facial landmarks; Riemannian geometry

机器视觉

生成对抗; 数据扩增; 人脸标志检测; 表情识别

摘要(Abstract)

In this work, we propose a novel approach for generating videos of the six basic facial expressions given a neutral face image.

在这项工作中，我们提出了一种新的方法来生成视频的六个基本面部表情给定一个中立的人脸图像。.

We propose to exploit the face geometry by modeling the facial landmarks motion as curves encoded as points on a hypersphere.

我们建议通过将面部地标运动建模为超球面上编码为点的曲线来利用面部几何。.

By proposing a conditional version of manifold-valued Wasserstein generative adversarial network (GAN) for motion generation on the hypersphere, we learn the distribution of facial expression dynamics of different classes, from which we synthesize new facial expression motions.

通过提出一种用于超球面运动生成的流形值Wasserstein生成对抗网络（GAN）的条件版本，我们了解了不同类别的面部表情动力学分布，并从中合成了新的面部表情运动。.

The resulting motions can be transformed to sequences of landmarks and then to images sequences by editing the texture information using another conditional Generative Adversarial Network.

通过使用另一个条件生成对抗网络编辑纹理信息，可以将生成的运动转化为地标序列，然后转化为图像序列。.

To the best of our knowledge, this is the first work that explores manifold-valued representations with GAN to address the problem of dynamic facial expression generation.

据我们所知，这是第一个利用GAN探索多值表示以解决动态面部表情生成问题的工作。.

We evaluate our proposed approach both quantitatively and qualitatively on two public datasets; Oulu-CASIA and MUG Facial Expression.

我们在两个公共数据集上对我们提出的方法进行了定量和定性评估；Oulu CASIA和MUG的面部表情。.

Our experimental results demonstrate the effectiveness of our approach in generating realistic videos with continuous motion, realistic appearance and identity preservation.

我们的实验结果证明了我们的方法在生成具有连续运动、真实外观和身份保持的真实视频方面的有效性。.

We also show the efficiency of our framework for dynamic facial expressions generation, dynamic facial expression transfer and data augmentation for training improved emotion recognition models…

我们还展示了我们的框架在动态面部表情生成、动态面部表情传输和数据增强方面的效率，用于训练改进的情绪识别模型。。.

作者(Authors)

[‘Naima Otberdout’, ‘Mohamed Daoudi’, ‘Anis Kacem’, ‘Lahoucine Ballihi’, ‘Stefano Berretti’]