Overview of Input-based Facial Expression Generation and Latest Applications

Expression generation technology is an important part of the field of artificial intelligence research. As a hot issue in computer applications today, its results have been widely used in human-computer interaction, digital entertainment, communications, video conferencing, and medical fields.This article summarizes the published research methods based on input methods into image and text input control expression generation methods, and reviews them. The image input control expression generation method is divided into two cases according to the presence or absence of constraints. Most model algorithms propose solutions to improve the coincidence of natural images and application models in pixel space. This article discusses typical successes in terms of theory, technology, etc., analyzes the characteristics of different algorithms, current problems, and future development directions, and provides references for related research.

[1]  L. F Abbott,et al.  Lapicque’s introduction of the integrate-and-fire model neuron (1907) , 1999, Brain Research Bulletin.

[2]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Gao We.  SYNTHESIS OF FACIAL BEHAVIOR FOR VIRTUAL HUMAN , 1998 .

[4]  Bogdan Raducanu,et al.  Invertible Conditional GANs for image editing , 2016, ArXiv.

[5]  Chitta Baral,et al.  Visual Commonsense for Scene Understanding Using Perception, Semantic Parsing and Reasoning , 2015, AAAI Spring Symposia.

[6]  Xiaogang Wang,et al.  StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  P. Ekman.  Are there basic emotions? , 1992, Psychological review.

[8]  Yong Tao,et al.  Compound facial expressions of emotion , 2014, Proceedings of the National Academy of Sciences.

[9]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[10]  Ruslan Salakhutdinov,et al.  Generating Images from Captions with Attention , 2015, ICLR.

[11]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Jianfei Cai,et al.  Conditional Adversarial Synthesis of 3D Facial Action Units , 2018, Neurocomputing.

[13]  Andrew S. Glassner,et al.  Proceedings of the 27th annual conference on Computer graphics and interactive techniques , 1994, SIGGRAPH 1994.

[14]  Birgit Lugrin,et al.  In the Face of Emotion: A Behavioral Study on Emotions Towards a Robot Using the Facial Action Coding System , 2017, HRI.

[15]  Li Xudong.  Image Morphing Method for Facial Expression Image and Animation Synthesis , 2007 .

[16]  Francesc Moreno-Noguer,et al.  GANimation: Anatomically-aware Facial Animation from a Single Image , 2018, ECCV.

[17]  Yuchi Huang,et al.  DyadGAN: Generating Facial Expressions in Dyadic Interactions , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[18]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[19]  Synthesizing Pictures From Text Using a DC-GAN , 2017 .

[20]  Lance Williams,et al.  Animating images with drawings , 1994, SIGGRAPH.

[21]  Philip Bachman,et al.  Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data , 2018, ICML.

[22]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[23]  Jean-Marc Odobez,et al.  Robust and Accurate 3D Head Pose Estimation through 3DMM and Online Head Model Reconstruction , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[24]  Yoshua Bengio,et al.  Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Zhe Gan,et al.  AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Yizhou Yu,et al.  DeepSketch2Face , 2017, ACM Trans. Graph..

[27]  Ifigeneia Mavridou,et al.  FACETEQ interface demo for emotion expression in VR , 2017, 2017 IEEE Virtual Reality (VR).

[28]  Xiaogang Wang,et al.  FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.