Zhigang Deng

(Full) Professor, Ph.D.
   Director of Graduate Studies,
   Director of Computer Graphics
         & Interactive Media Lab,
Department of Computer Science,
University of Houston, Houston, TX

Office:
Phillip G. Hoffman Hall (PGH), Rm 219
Houston, TX 77204-3010

Tel: +1 713 743 1018
Fax: +1 713 743 3335

Email (preferred way to contact me):
zdeng4 (at) uh.edu

Mailing Address:
Phillip G. Hoffman Hall, Department of Computer Science,
3551 Cullen Blvd, Room 501,
Houston, TX, 77204-3010

biography

Dr. Zhigang Deng is currently a (Full) Professor of Computer Science at University of Houston (UH). He is also the Director of Graduate Studies at UH Computer Science Department, and the Director of the UH Computer Graphics and Interactive Media (CGIM) Lab. He earned Ph.D. in Computer Science at the Department of Computer Science at the University of Southern California in 2006. He also completed B.S. degree in Mathematics from Xiamen University (China), and M.S. in Computer Science from Peking University (China). Over the years, he had worked at or consulted for the Founder Group (China), AT&T Research, Tencent USA, and Qualcomm.

His current research interests are in the broad areas of graphics/animation, human computer interaction, virtual human modeling & animation, and robotics. He is the recipient of many awards including CASA Best Paper Awards (or runner-up) (2 times), ACM ICMI Ten Year Technical Impact Award (2014), UH Teaching Excellence Award (2013), NSFC Overseas and Hong Kong/Macau Young Scholars Collaborative Research Award (2013), ICRA Best Medical Robotics Paper Award Runner-up (2012), and Google Faculty Research Award (2010). He had been the CASA 2014 conference general co-chair and SCA 2015 conference general co-chair. His research has been funded by NSF, NIH, NASA, DOD, Texas NHARP, and various industry sources (Google, Honda, etc). His research work has been incorporated into many de facto graphics/animation packages (including Maya, Houdini, and Blender) and used in many game studios (e.g., Electronic Arts and Naughty Dog). He is a senior member of ACM and a senior member of IEEE.

Research Opportunities

I am constantly looking for new graduate or undergraduate students to join my group! Self-Motivated students with solid math, vision, or graphics background are encouraged to apply. If you are already a current MS or PhD student in UH Computer Science program and would like to work with me, please make sure to take COSC6372 and/or COSC6356 courses.

home     projects     vita     group     demo

selected current projects

Real-time Video-based Facial Performance Capture and Manipulation

Automatic algorithms to real-time capture 3D high-quality facial mesh sequences as well as video-based facial expression manipulation

Understand and Modeling Human Behaviors in Multiparty Conversations

Quantifying, understanding, and modeling human behaviors and gestures when they are involved with multiparty conversations

Robust Structure Simplification for Hex Re-meshing

A robust and automatic algorithm to simplify the structure and reduce the singularities of a hexahedral mesh
[Source Code]

Interactive Complex Object Modeling from Multi-view Images

development of a novel interactive modeling approach based on multi-view images including interactive 3D modeling and stochastic motion parameter estimation.

Hexahedral Mesh Generation, Optimization, and Evaluation

A first and complete pipeline to optimize the global structure of a hex-mesh, by identifying and removing those valid removal base-complex sheets that contain misaligned singularities, and a volumetric partitioning strategy based on a generalized sweeping framework to seamlessly partition the volume of an input triangle mesh into a collection of deformed cuboids.

Robust and Accurate Skeletal Rigging from Mesh/Point Sequences

Using the input of an animated mesh sequence, this approach can automatically extract its optimal skeleton structure, joint positions, linear blend skinning weights, and the corresponding bone transformations.

Live Speech Driven Facial Animation

Fully-automated algorithms to generate realistic lip-sync and head-and-eye animations based on live speech input alone, which can run in real-time on an off-the-shelf computer.

Two-layer Sparse Compression of Dense-Weight Blend Skinning

It introduces an efficient two-layer sparse compression technique to substantially reduce the computational cost of a dense-weight skinning model, with insignificant loss of its visual quality.

Smooth Skinning Decomposition with Rigid Bones

The SSDR model can effectively approximate the skin deformation of nearly articulated models as well as highly deformable models by a low number of rigid bones and a sparse, convex bone-vertex weight map.

Realistic Traffic Simulation and Evaluation

Design of novel and efficient algorithms and systems to simulate large-scale realistic traffic in various road and urban settings, including mixed traffic, lane-changing, simulated traffic evaluation, and intersectional traffic simulation.

Latest News
Our SSDR work ("Smooth Skinning Decomposition with Rigid Bones", Siggraph Asia 2012) has been incorporated into many mainstream graphics/animation packages, including Maya, Houdini, and Blender, and has been used in many game studios including Electronic Arts (EA) and Naughty Dog.
The open-source code of our SSDR work can be found in this LINK. Also check out this UH NSM News.
Our paper "Robust Structure Simplification for Hex Re-meshing" was accepted to ACM SIGGRAPH Asia 2017 Conference as a full technical paper.
Our paper "Topologically Consistent Leafy Tree Morphing" won the Best Paper Award on the International Conference on Computer Animation and Social Agents (CASA) 2017.
Our paper "eye contact based speaker identification in multiparty conversations" was accepted to ACM CHI 2017 Conference as a full research paper.
I am officially promoted to a Full Professor at UH Computer Science Department, Effective on 9/1/2016 (after working exactly ten years at UH).
I together with Prof. Chen receive a new DoD DURIP grant to build a scalable high-fidelity visual computing infrastructure at University of Houston.
I receive a Faculty Academic Excellence Award in recognition extraordinary academic achievements from the Department of Computer Science at University of Houston, during the Department's 2015 annual award recognition event.
I receive a new NSF research grant to work on "Digitally Mediated Multi-party Communication" which starts on 9/1/2015.
I am appointed as the new Director of Graduate Studies in the Department of Computer Science at UH, which will be effective since September 2015.
Our paper titled "Hexahedral Mesh Re-parameterization from Aligned Base Domains" (with X. Gao and G. Chen) is accepted to ACM SIGGRAPH 2015 Conference as a technical paper.
I receive a Certificate of Excellence in recognition extraordinary achievements from College of Natural Sciences and Mathematics at University of Houston, during the Provost's 2014 award recognition luncheon.
I am a co-recipient of "Ten Year Technical Impact Award" (on ACM ICMI 2014 Conference) for my co-authored ICMI 2004 paper "Analysis of Emotion Recognition using Facial Expressions, Speech and Multimodal Information".
I serve as a general co-chair of ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA) 2015 that will be held at Los Angeles, CA. Here is the official SCA 2015 website.
I co-instruct a half-day "Skinning: Real-time Shape Deformation" course (with A. Jacobson, L. Kavan, and J. Lewis) on the ACM SIGGRAPH 2014 Conference.
Our paper titled "Robust and Accurate Skeletal Rigging from Mesh Sequences" (with my PhD student Binh H. Le) was accepted to ACM SIGGRAPH 2014 Conference as a technical paper.