Jen-Yuan Chiang

Learn More
We present a novel method for acquisition, modeling, compression, and synthesis of realistic facial deformations using polynomial displacement maps. Our method consists of an analysis phase where the relationship between motion capture markers and detailed facial geometry is inferred, and a synthesis phase where novel detailed animated facial geometry is(More)
For more than three decades, computer graphics researchers have been working to create a photorealistic digital actor. In the Digital Emily project, Image Metrics and the University of Southern California's Institute for Creative Technologies (USC ICT) animated a digital face using new results in 3D facial capture, character modeling, animation, and(More)
We present a novel technique for acquiring detailed facial geometry of a dynamic performance using extended spherical gradient illumination. Key to our method is a new algorithm for <i>jointly</i> aligning two photographs, under a gradient illumination condition and its complement, to a full-on tracking frame, providing dense temporal correspondences under(More)
Introduction We developed a high-resolution, real-time facial performance capture system based on a spherical gradient photometric stereo technique [Ma et al. 2007] and multi-view stereo. We use four spherical gradient illumination patterns to estimate normal maps of subjects. A structured-light-assisted two-view stereo system is employed to acquire 3D(More)
In this work, we develop a real-time geometry capture approach to digital face replacement for a dynamic performance. Digital face replacement has major applications in visual effects for motion pictures as well as interactive applications such as video games and simulation and training environments. Our approach looks into extending the 3D face scanning(More)
The Session Initiation Protocol (SIP) provides advanced signaling and control functionality for a wide variety of multimedia services. This paper introduces an extension of Session Initiation Protocol (SIP) to support multipoint conference. Via functions, a multipoint conference could be constructed by mobile hosts (User Agents, UAs). It requires no server(More)
In this article we describe the software-controllable spectral capabilities available in OFDM based UWB signals. Here we intend to show how MB-OFDM signal might adapt local regulations, remedy future interference situations prepare UWB for the opportunities of cognitive radio. Spectrum sculpting for interference control is more easier and more effective(More)
Capturing facial geometry that is high-resolution, yet easy to animate, remains a difficult challenge. While a single scanned geometry may be straightforward to animate smoothly, it may not always yield realistic fine scale detail when deformed into different facial expressions. Combining scans of multiple facial expressions, however, is only practical if(More)
Joint first author †Contact person ‡Email: {jsyeh, liubiti, richardg, lifong, yuminyung, jean, jonathan, yolux, dynamic, cyy, robin, ming}@cmlab.csie.ntu.edu.tw The first component is a multi-camera system. Game players stand on a stage with several cameras surrounding them. Our capturing system uses background matting to segment the human body from the(More)
  • 1