FAA

Face tracking is an extensively studied field. Nevertheless, it is still a challenge to make a robust and efficient face tracker, especially on mobile devices. This extended abstract briefly describes our implementation of a high-performance multi-...

The importance of modeling speech articulation for high-quality audiovisual (AV) speech synthesis is widely acknowledged. Nevertheless, while state-of-the-art, data-driven approaches to facial animation can make use of sophisticated motion capture ...

The 3D capture of facial performance has become a necessary tool for delivering visual effects related to an actor's face or for creating new realistic characters. We present a novel system using a practical acquisition setup without active illumination ...

The approximation of realistic facial expressions is an essential part of many virtual simulations, such as video games or avatar applications. Unfortunately, a lot of manual work is usually needed to create realistic facial expressions. In this paper, ...

The eyes play an essential role during face to face communication. They provide important information about visual attention and turn-taking during human-human and human-avatar interaction. In fact, the eye is a complex organ and gaze is only one of its ...

For decades, morphological research on human faces was performed either on the living subject, or by means of 2D photographs. Within the last few years and with the development of new systems we are now able to produce three dimensional models of human ...

In recent years, the use of virtual agents that act as an interface between human and computer has become increasingly popular. Such agents typically appear as embodied characters and display various types of life-like behaviour. To ensure the ...

The number and quality of smartphones on the market has dramatically raised lately. Researchers and developers are, thus, more and more pushed to bring algorithms and techniques from desktop environments to mobile platforms. One of the biggest ...

Masahiro Mori, who introduced the concept of the Uncanny Valley, recommended settling for moderate levels of human likeness in robotic design in order to avoid the eeriness upon encountering entities closely resembling humans [Mori 1970]. However, the ...

In the vast majority of recent works, data-driven audiovisual speech synthesis, i.e., the generation of face animation together with the corresponding acoustic speech, is still considered as the synchronization of two independent sources: synthesized ...

The original theory of the uncanny valley (see Figure 1) has been proposed by the Japanese scientist Masahiro Mori in 1970 [1970], where he supposed that likeability of robots does not linearly increase with human likeness. Instead, the likeability ...

This work is part of the long term project of the Department of Computer Engineering and Industrial Automation (DCA) of University of Campinas of developing videorealistic interactive conversational agents to provide more intuitive and efficient human-...

Imitation of natural facial behavior in real-time is still challenging when it comes to natural behavior such as laughter and nonverbal expressions. This paper explains our ongoing work on methodologies and tools for estimating Facial Animation ...

Trust is a key aspect to human communication due to its link to co-operation and survival. Recent research by [Ballew and Todorov 2007] has shown that humans can generate an initial trustworthiness judgement based on facial features within 100ms. ...

The ability to animate a 3D virtual character in real-time has great potential in terms of connecting and interacting with the audience, for example allowing a virtual character to answer questions from audience members or make spontaneous comments ...

The simulation of facial movements is a difficult task because the complex and sophisticated structure of the human head involves the motion, deformation, and contact handling between bio-tissues that are viscoelastic, nonlinear, anisotropic, and ...

In this article, we present HapFACS 1.0, a new software/API for generating static and dynamic three-dimensional facial expressions based on the Facial Action Coding System (FACS). HapFACS provides total control over the FACS Action Units (AUs) activated ...