612 Hits in 9.7 sec

Deep Learning Augmented Realistic Avatars for Social VR Human Representation

Matthijs van der Boon, Leonor Fermoselle, Frank ter Haar, Sylvie Dijkstra-Soudarissanane, Omar Niamut
2022 ACM International Conference on Interactive Media Experiences  
The deep learning modules efectively improve the visual representation of the avatar and show how AI techniques can be integrated with traditional animation methods to generate realistic human avatars  ...  The second module runs inference in real-time at the rendering stage and performs a style transfer to the avatar's eyes.  ...  The avatar is animated with the eye gaze and facial expressions of the user using the Eye and Facial Tracking SDK.  ... 
doi:10.1145/3505284.3532976 fatcat:crpdpirdtfctnd272fcnzdmf7u

Video-based facial re-animation

Wolfgang Paier, Markus Kettern, Anna Hilsmann, Peter Eisert
2015 Proceedings of the 12th European Conference on Visual Media Production - CVMP '15  
We present an inexpensive method for video-based facial animation, which combines the photorealism of real videos with the flexibility of CGI-based animation by extracting dynamic texture sequences from  ...  Video sequences on the other hand need to be captured prior to the animation stage and do not offer the same animation flexibility as computer graphics models.  ...  Acknowledgment This work is partially funded by the European Commission, H2020-644629 AutoPost.  ... 
doi:10.1145/2824840.2824843 dblp:conf/cvmp/PaierKHE15 fatcat:grx6jmprjjbqhip3bmqljocrku

Animated CharToon faces

Zsófia Ruttkay, Han Noot
2000 Proceedings of the first international symposium on Non-photorealistic animation and rendering - NPAR '00  
In human-computer interaction, because of the lack of sufficient knowledge and appropriate tools to model and animate realistic 3D faces, 2D cartoon faces are feasible alternatives with the extra appeal  ...  We discuss CharToon, an interactive system to design and animate 2D cartoon faces. We give illustrations (also movies on CD) of the expressive and artistic effects which can be produced.  ...  Hendrix for turning captured date into animations, and for the FASE group at TUD for providing captured data.  ... 
doi:10.1145/340916.340928 dblp:conf/npar/RuttkayN00 fatcat:qcaavxramzaojfaqt4n6s3yuxa

The SARA Project

Diana Arellano, Volker Helzle, Ulrich Max Schaller, Reinhold Rauh, Marc Spicker, Oliver Deussen
2015 Proceedings of the XVI International Conference on Human Computer Interaction - Interacción '15  
Although the project is currently in an ongoing phase, it shows the potential of using virtual characters and real-time techniques for interactive experiments, which otherwise would be impossible using  ...  SARA is an ongoing research project that investigates in a novel and artistic way the causes for social communication and emotion recognition deficits in children and adolescents with high-functioning  ...  The SARA project (officially Impact of Non-Photorealistic Rendering for the understanding of emotional facial expressions by children and adolescents with high-functioning Autism Spectrum Disorders is  ... 
doi:10.1145/2829875.2829884 dblp:conf/interaccion/ArellanoHSRSD15 fatcat:3su7iafv3jg33erqjv5yauh6hq

NARRATE: A Normal Assisted Free-View Portrait Stylizer [article]

Youjia Wang, Teng Xu, Yiwen Wu, Minzhang Li, Wenzheng Chen, Lan Xu, Jingyi Yu
2022 arXiv   pre-print
We extend Total Relighting to fix this problem by unifying its multi-view input normal maps with the physical face model.  ...  As a hybrid neural-physical face model, NARRATE leverages complementary benefits of geometry-aware generative approaches and normal-assisted physical face models.  ...  Facial Animation NARRATE can be integrated with facial animation tools for creating realistic animated avatars.  ... 
arXiv:2207.00974v2 fatcat:nfdedy34jjdrto4su7sn7xtmmi

Deep Semantic Manipulation of Facial Videos [article]

Girish Kumar Solanki, Anastasios Roussos
2021 arXiv   pre-print
avatars for video games and virtual assistants.  ...  Our method supports semantic video manipulation based on neural rendering and 3D-based facial expression modelling.  ...  They also have the potential to be beneficial for research and applications in psychology and psychiatry, since modelling and analyzing the facial expressions can play an important role in diagnosing and  ... 
arXiv:2111.07902v1 fatcat:q7bc6r6ryvaibif4zrfyhytu4q

A computer-generated animated face stimulus set for psychophysiological research

Adam Naples, Alyssa Nguyen-Phuc, Marika Coffman, Anna Kresse, Susan Faja, Raphael Bernier, James C. McPartland
2014 Behavior Research Methods  
All faces are standardized in terms of size, luminance, and location and size of facial features. Each face begins with a neutral pose and transitions to an expression over the course of 30 frames.  ...  Altogether there are 222 stimuli spanning 3 different categories of movement: (1) an affective movement (fearful face); (2) a neutral movement (close-lipped, puffed cheeks with open eyes); and (3) a biologically  ...  The resulting "impossible" faces involve an upward dislocation of the eyes and mouth while maintaining the integrity of the face structure.  ... 
doi:10.3758/s13428-014-0491-x pmid:25028164 pmcid:PMC4297263 fatcat:f6dk7bmap5cz3frdamoastwzey

Non-Photorealistic Rendering of Portraits [article]

Paul L. Rosin, Yu-Kun Lai
2015 Computational Aesthetics in Graphics  
The second style is inspired by the artist Julian Opie, in which the human face is reduced to its essentials, i.e. homogeneous skin, thick black lines, and facial features such as eyes and the nose represented  ...  We describe an image-based non-photorealistic rendering pipeline for creating portraits in two styles: The first is a somewhat "puppet" like rendering, that treats the face like a relatively uniform smooth  ...  Acknowledgements The following source images have been made available on Flickr under the creative commons license by the following members: figure 3  ... 
doi:10.2312/exp.20151189 fatcat:mekf3lqytnbifpwy3x4onzo22e

Geometry-driven photorealistic facial expression synthesis

Qingshan Zhang, Z. Liu, Gaining Quo, D. Terzopoulos, Heung-Yeung Shum
2006 IEEE Transactions on Visualization and Computer Graphics  
Expression mapping (also called performance driven animation) has been a popular method for generating facial animations.  ...  We have developed a technique to infer the missing feature point motions from the tracked subset by using an example-based approach.  ...  ACKNOWLEDGMENTS The authors thank Ying Song, who implemented the geometric deformation system for the scanned 3D head model.  ... 
doi:10.1109/tvcg.2006.9 pmid:16382607 fatcat:zubm4ghz4fdv5adtijsnrwraki

Computer Facial Animation: A Review

Heng Yu Ping, Lili Nurliyana Abdullah, Puteri Suhaiza Sulaiman, Alfian Abdul Halin
2013 Journal of clean energy technologies  
Facial modelling and facial animation are important in developing realistic computer facial animation. Both modelling and animation is dependent to drive the animation.  ...  However, animating human face still presents interesting challenges because of its familiarity as the face is the part used to recognize individuals.  ...  Some claims that a good facial modelling and animation involving how to lip synchronization and how to use the eyes, brows and lids for expression [3] .  ... 
doi:10.7763/ijcte.2013.v5.770 fatcat:mwvovs2qz5eotaq5ppujfmsnky

Modeling Living Systems for Computer Vision

Demetri Terzopoulos
1995 International Joint Conference on Artificial Intelligence  
Currently, artificial faces support a model-based approach to facial image analysis. In the future, it should be possible to incorporate brains and some degree of intelligence into them as well.  ...  Although the modeling of all aspects of living systems is a worthwhile endeavor in its own right, the emphasis here will be on the modeling of animals, including humans, for computer vision.  ...  I thank Keith Waters for our years of collaboration on facial modeling.  ... 
dblp:conf/ijcai/Terzopoulos95 fatcat:hc4r5p65r5fbdbxz3lrx4k5u7e

FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning [article]

Chenxu Zhang, Yifan Zhao, Yifei Huang, Ming Zeng, Saifeng Ni, Madhukar Budagavi, Xiaohu Guo
2021 arXiv   pre-print
To model such complicated relationships among different face attributes with input audio, we propose a FACe Implicit Attribute Learning Generative Adversarial Network (FACIAL-GAN), which integrates the  ...  phonetics-aware, context-aware, and identity-aware information to synthesize the 3D face animation with realistic motions of lips, head poses, and eye blinks.  ...  GAN module to integrate phonetic, contextual, and personalized information of the talking, and combine the synthesized 3D model with AU attention map to generate photorealistic videos with synchronized  ... 
arXiv:2108.07938v1 fatcat:2nodbkvg3rh3fifbfnc2byowjy

Is that a smile?

Vidya Setlur, Bruce Gooch
2004 Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering - NPAR '04  
The foveal and peripheral components of the human visual system tend to interpret emotional states differently, adding a degree of elusiveness to the facial image.  ...  Our technique first isolates the coarser low spatial frequency components and finer high spatial frequency details from two images with differing facial expressions.  ...  Acknowledgements We would like to thank the reviewers for their valuable suggestions and feedback. Thanks to Kathryn Farley, and Dan Zellner for providing us with their facial expressions.  ... 
doi:10.1145/987657.987670 dblp:conf/npar/SetlurG04 fatcat:royxmfmizverrmeypdowhptfeq

A parameterized digital 3D model of the Rhesus macaque face for investigating the visual processing of social cues

Aidan P. Murphy, David A. Leopold
2019 Journal of Neuroscience Methods  
neural specialization for faces found in the primate.  ...  The results herald a new set of possibilities in adaptive sampling of a high-dimensional and socially meaningful feature space, thus opening the door to systematic testing of hypotheses about the abundant  ...  Acknowledgements The authors thank the following sources for sharing CT data:  ... 
doi:10.1016/j.jneumeth.2019.06.001 pmid:31229584 pmcid:PMC7446874 fatcat:dusr6uwfnvadtnp2z3xqf64f6a

The X-Faces Behind the Portraits of No One

João Correia, Tiago Martins, Sérgio Rebelo, João Bicker, Penousal Machado
2021 SN Computer Science  
This paper presents our work on the computational creation of photorealistic face images with a focus on how we transformed our generative and evolutionary system X-Faces into an interactive Media Art  ...  The result, the interactive installation Portraits of No One, synthesis and displays facial portraits on the borderline between the real and artificial using the facial features captured from its audience  ...  Acknowledgements The third author is funded by Foundation for Science and Technology (FCT) under the Grant SFRH/BD/132728/2017.  ... 
doi:10.1007/s42979-021-00604-w dblp:journals/sncs/CorreiaMRBM21 fatcat:6qxde2f7fbew3lmexellcptubq
« Previous Showing results 1 — 15 out of 612 results