Search For:

Displaying 1-29 out of 29 total
Live Speech Driven Head-and-Eye Motion Generators
Found in: IEEE Transactions on Visualization and Computer Graphics
By B. H. Le, Xiaohan Ma, Zhigang Deng
Issue Date:November 2012
pp. 1902-1914
This paper describes a fully automated framework to generate realistic head motion, eye gaze, and eyelid motion simultaneously based on live (or recorded) speech input. Its central idea is to learn separate yet interrelated statistical models for each comp...
 
A Statistical Quality Model for Data-Driven Speech Animation
Found in: IEEE Transactions on Visualization and Computer Graphics
By Xiaohan Ma, Zhigang Deng
Issue Date:November 2012
pp. 1915-1927
In recent years, data-driven speech animation approaches have achieved significant successes in terms of animation quality. However, how to automatically evaluate the realism of novel synthesized speech animations has been an important yet unsolved researc...
 
Characterizing the Performance and Power Consumption of 3D Mobile Games
Found in: Computer
By Xiaohan Ma,Zhigang Deng,Mian Dong,Lin Zhong
Issue Date:April 2013
pp. 76-82
A preliminary study using the Quake 3 and XRace games as benchmarks on three mainstream mobile system-on-chip architectures reveals that the geometry stage is the main bottleneck in 3D mobile games and confirms that game logic significantly affects power c...
 
Intraoperative registration of preoperative 4D cardiac anatomy with real-time MR images
Found in: 2012 IEEE 12th International Conference on Bioinformatics & Bioengineering (BIBE)
By Xifeng Gao,Nikhil V. Navkar,Dipan J. Shah,Nikolaos V. Tsekos,Zhigang Deng
Issue Date:November 2012
pp. 583-588
Co-registering pre- and intra- operative MR data is an important yet challenging problem due to different acquisition parameters, resolutions, and plane orientations. Despite its importance, previous approaches are often computationally intensive and thus ...
 
Crafting Personalized Facial Avatars Using Editable Portrait and Photograph Example
Found in: Virtual Reality Conference, IEEE
By Tanasai Sucontphunt, Zhigang Deng, Ulrich Neumann
Issue Date:March 2009
pp. 259-260
Computer-generated facial avatars have been increasingly used in a variety of virtual reality applications. Emulating the real-world face sculpting process, we present an interactive system to intuitively craft personalized 3D facial avatars by using 3D po...
 
Natural Eye Motion Synthesis by Modeling Gaze-Head Coupling
Found in: Virtual Reality Conference, IEEE
By Xiaohan Ma, Zhigang Deng
Issue Date:March 2009
pp. 143-150
Due to the intrinsic subtlety and dynamics of eye movements, automated generation of natural and engaging eye motion has been a challenging task for decades. In this paper we present an effective technique to synthesize natural eye gazes given a head motio...
 
Orthogonal-Blendshape-Based Editing System for Facial Motion Capture Data
Found in: IEEE Computer Graphics and Applications
By Qing Li, Zhigang Deng
Issue Date:November 2008
pp. 76-82
The authors present a novel data-driven 3D facial motion capture data editing system using automated construction of an orthogonal blendshape face model and constrained weight propagation, aiming to bridge the popular facial motion capture technique and bl...
 
Expressive Facial Animation Synthesis by Learning Speech Coarticulation and Expression Spaces
Found in: IEEE Transactions on Visualization and Computer Graphics
By Zhigang Deng, Ulrich Neumann, J.P. Lewis, Tae-Yong Kim, Murtaza Bulut, Shrikanth Narayanan
Issue Date:November 2006
pp. 1523-1534
<p><b>Abstract</b>—Synthesizing expressive facial animation is a very challenging topic within the graphics community. In this paper, we present an expressive facial animation synthesis system enabled by automated learning from facial mot...
 
Automated Eye Motion Using Texture Synthesis
Found in: IEEE Computer Graphics and Applications
By Zhigang Deng, J.P. Lewis, Ulrich Neumann
Issue Date:March 2005
pp. 24-30
Modeling and animating human eyes requires special care, because, as the
 
GPU-Accelerated Interactive Visualization and Planning of Neurosurgical Interventions
Found in: IEEE Computer Graphics and Applications
By Mario Rincon-Nigro,Nikhil V. Navkar,Nikolaos V. Tsekos, Zhigang Deng
Issue Date:January 2014
pp. 22-31
Advances in computational methods and hardware platforms provide efficient processing of medical-imaging datasets for surgical planning. For neurosurgical interventions employing a straight access path, planning entails selecting a path from the scalp to t...
 
Marker Optimization for Facial Motion Acquisition and Deformation
Found in: IEEE Transactions on Visualization and Computer Graphics
By B. H. Le, Mingyang Zhu, Zhigang Deng
Issue Date:November 2013
pp. 1859-1871
A long-standing problem in marker-based facial motion capture is what are the optimal facial mocap marker layouts. Despite its wide range of potential applications, this problem has not yet been systematically explored to date. This paper describes an appr...
 
Generating Freestyle Group Formations in Agent-Based Crowd Simulations
Found in: IEEE Computer Graphics and Applications
By Qin Gu, Zhigang Deng
Issue Date:January 2013
pp. 20-31
Few crowd simulation algorithms take collective group features such as group formations into consideration. Recent approaches often manually specify hard constraints such as predefined keyframe agent formations and interpolate them during the simulation. A...
 
Context-Aware Motion Diversification for Crowd Simulation
Found in: IEEE Computer Graphics and Applications
By Qin Gu, Zhigang Deng
Issue Date:September 2011
pp. 54-65
Traditional crowd simulation models typically focus on navigational pathfinding and local collision avoidance. Little research has explored how to optimally control individual agents' detailed motions throughout a crowd. A proposed approach dynamically con...
 
Reachability Analysis of Cost-Reward Timed Automata for Energy Efficiency Scheduling
Found in: Proceedings of Programming Models and Applications on Multicores and Manycores (PMAM'14)
By Guo Dong, Guosun Zeng, Huanliang Xiong, Wei Liu, Wei Wang, Zhigang Deng
Issue Date:February 2014
pp. 140-148
As the ongoing scaling of semiconductor technology causing severe increase of on-chip power density in microprocessors, this leads for urgent requirement for power management during each level of computer system design. In this paper, we describe an approa...
     
Cost-based workload balancing for ray tracing on multi-GPU systems
Found in: ACM SIGGRAPH 2013 Posters (SIGGRAPH '13)
By Mario Rincón-Nigro, Zhigang Deng
Issue Date:July 2013
pp. 1-1
Ray tracing is at the core of most techniques for creating realistic imagery. Parallel implementations of ray tracing handle the irregular workload through task systems. The strengths of static and dynamic scheduling strategies are complementary to each ot...
     
Two-layer sparse compression of dense-weight blend skinning
Found in: ACM Transactions on Graphics (TOG)
By Binh Huy Le, Zhigang Deng
Issue Date:July 2013
pp. 1-10
Weighted linear interpolation has been widely used in many skinning techniques including linear blend skinning, dual quaternion blend skinning, and cage based deformation. To speed up performance, these skinning models typically employ a sparseness constra...
     
Smooth skinning decomposition with rigid bones
Found in: ACM Transactions on Graphics (TOG)
By Binh Huy Le, Zhigang Deng
Issue Date:November 2012
pp. 1-10
This paper introduces the Smooth Skinning Decomposition with Rigid Bones (SSDR), an automated algorithm to extract the linear blend skinning (LBS) from a set of example poses. The SSDR model can effectively approximate the skin deformation of nearly articu...
     
A robust high-capacity affine-transformation-invariant scheme for watermarking 3D geometric models
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Caiming Zhang, Xifeng Gao, Yan Huang, Zhigang Deng
Issue Date:September 2012
pp. 1-21
In this article we propose a novel, robust, and high-capacity watermarking method for 3D meshes with arbitrary connectivities in the spatial domain based on affine invariants. Given a 3D mesh model, a watermark is embedded as affine-invariant length ratios...
     
Perceptual analysis of talking avatar head movements: a quantitative perspective
Found in: Proceedings of the 2011 annual conference on Human factors in computing systems (CHI '11)
By Binh Huy Le, Xiaohan Ma, Zhigang Deng
Issue Date:May 2011
pp. 2699-2702
Lifelike interface agents (e.g. talking avatars) have been increasingly used in human-computer interaction applications. In this work, we quantitatively analyze how human perception is affected by audio-head motion characteristics of talking avatars. Speci...
     
Perceiving motion transitions in pedestrian crowds
Found in: Proceedings of the 17th ACM Symposium on Virtual Reality Software and Technology (VRST '10)
By Chang Yun, Qin Gu, Zhigang Deng
Issue Date:November 2010
pp. 199-202
Perception of motion transitions in a pedestrian crowd is affected by many collective features such as crowd density, appearance variations, motion variations, and sub-group interaction patterns. We conducted a series of psychophysical experiments to inves...
     
3D human face identity transfer using deformation gradient
Found in: ACM SIGGRAPH 2010 Posters (SIGGRAPH '10)
By Tanasai Sucontphunt, Ulrich Neumann, Zhigang Deng
Issue Date:July 2010
pp. 1-1
Modeling a 3D face toward a specific person is a tedious and painstaking task even for skilled artists. Crafting a 3D cartoon-style or a 3D fiction-creature face to reflect a specific person likeness is even more challenging. For example, creating an ogre ...
     
Style learning and transferring for facial animation editing
Found in: Proceedings of the 2009 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA '09)
By Binh Huy Le, Xiaohan Ma, Zhigang Deng
Issue Date:August 2009
pp. 123-132
Most of current facial animation editing techniques are frame-based approaches (i.e., manually edit one keyframe every several frames), which is ineffective, time-consuming, and prone to editing inconsistency. In this paper, we present a novel facial editi...
     
Can local avatars satisfy a global audience? A case study of high-fidelity 3D facial avatar animation in subject identification and emotion perception by US and international groups
Found in: Computers in Entertainment (CIE)
By Chang Yun, Merrill Hiscock, Zhigang Deng
Issue Date:June 2009
pp. 1-8
This study investigates effectiveness of a local high-fidelity 3D facial avatar for a global audience by observing how US and International student groups differed in identifying subjects and perceiving emotions while viewing nonverbal high-fidelity 3D fac...
     
O' game, can you feel my frustration?: improving user's gaming experience via stresscam
Found in: Proceedings of the 27th international conference on Human factors in computing systems (CHI '09)
By Chang Yun, Dvijesh Shastri, Ioannis Pavlidis, Zhigang Deng
Issue Date:April 2009
pp. 1-4
One of the major challenges of video game design is to have appropriate difficulty levels for users in order to maximize the entertainment value of the game. Game players may lose interests if a game is either too easy or too difficult. This paper presents...
     
Perceptually consistent example-based human motion retrieval
Found in: Proceedings of the 2009 symposium on Interactive 3D graphics and games (I3D '09)
By Qin Gu, Qing Li, Zhigang Deng
Issue Date:February 2009
pp. 5-6
Large amount of human motion capture data have been increasingly recorded and used in animation and gaming applications. Efficient retrieval of logically similar motions from a large data repository thereby serves as a fundamental basis for these motion da...
     
Animating blendshape faces by cross-mapping motion capture data
Found in: Proceedings of the 2006 symposium on Interactive 3D graphics and games (SI3D '06)
By Pamela Fox, Pei-Ying Chiang, Ulrich Neumann, Zhigang Deng
Issue Date:March 2006
pp. 43-48
Animating 3D faces to achieve compelling realism is a challenging task in the entertainment industry. Previously proposed face transfer approaches generally require a high-quality animated source face in order to transfer its motion to new 3D faces. In thi...
     
Reducing blendshape interference by selected motion attenuation
Found in: Proceedings of the 2005 symposium on Interactive 3D graphics and games (SI3D '05)
By J. P. Lewis, Jonathan Mooser, Ulrich Neumann, Zhigang Deng
Issue Date:April 2005
pp. 25-29
Blendshapes (linear shape interpolation models) are perhaps the most commonly employed technique in facial animation practice. A major problem in creating blendshape animation is that of blendshape interference: the adjustment of a single blendshape "slide...
     
Analysis of emotion recognition using facial expressions, speech and multimodal information
Found in: Proceedings of the 6th international conference on Multimodal interfaces (ICMI '04)
By Abe Kazemzadeh, Carlos Busso, Chul Min Lee, Murtaza Bulut, Serdar Yildirim, Shrikanth Narayanan, Sungbok Lee, Ulrich Neumann, Zhigang Deng
Issue Date:October 2004
pp. 205-211
The interaction between human beings and computers will be more natural if computers are able to perceive and respond to human non-verbal communication such as emotions. Although several approaches have been proposed to recognize human emotions based on fa...
     
Audio-based head motion synthesis for Avatar-based telepresence systems
Found in: Proceedings of the 2004 ACM SIGMM workshop on Effective telepresence (ETP '04)
By Carlos Busso, Shri Narayanan, Ulrich Neumann, Zhigang Deng
Issue Date:October 2004
pp. 24-30
In this paper, a data-driven audio-based head motion synthesis technique is presented for avatar-based telepresence systems. First, head motion of a human subject speaking a custom corpus is captured, and the accompanying audio features are extracted. Base...
     
 1