Qing's Homepage

Qing Li (Resume)

Ph.D Student

Computer Graphics and Interactive Media Lab

Computer Science Department

University of Houston

E-mail: qingli12@cs.uh.edu

Projects

Facial Motion Capture Data Editing

We present a novel data-driven 3D facial motion capture data editing system by automated construction of an orthogonal blendshape face model and constrained weight propagation, aiming to bridge the popularized facial motion capture technique and blendshape approach. Given a collected facial motion capture dataset, we construct a truncated PCA space spanned by retained largest eigen-vectors and a corresponding blendshape face model for each anatomical region of the human face. As such, modifying blendshape weights (PCA coefficients) is equivalent to editing their corresponding motion capture sequence. In addition, a constrained weight propagation technique allows animators to balance automation and flexible controls. (PDF)

Example-based Human Motion Retrieval

We present a perceptually consistent, example-based human motion retrieval approach that is capable of efficiently searching for and ranking similar motion sequences given a query motion input. Our method employs a motion pattern discovery and matching scheme that breaks human motions into a part-based, hierarchical motion representation. Building upon this representation, a fast string match algorithm is used for efficient runtime motion query processing. We conducted comparative user studies to evaluate the accuracy and perceptualconsistency of our approach by comparing it with the state of the art example-based human motion search algorithms. (PDF)

Motion Capture Marker Labeling for Multiple Targets

We propose an online motion capture marker labeling approach for multiple interacting articulated targets. Given hundreds of unlabeled motion capture markers from multiple articulated targets that are interacting each other, our approach automatically labels these markers frame by frame, by fitting rigid bodies and exploiting trained structure and motion models. Advantages of our approach include: 1) our method is an online algorithm, which requires no user interaction once the algorithm starts. 2) Our method is more robust than traditional the closest point-based approaches by automatically imposing the structure and motion models. 3) Due to the use of the structure model which encodes the rigidity of each articulated body of captured targets, our method can recover missing markers robustly. (PDF)

Face Illumination Transformation

We present a novel image-based technique that transfers illumination from a source face image to a target face image based on the Logarithmic Total Variation (LTV) model. Our method does not require any prior information regarding the lighting conditions or the 3D geometries of the underlying faces.We first use a Radial Basis Functions (RBFs)-based deformation technique to align key facial features of the reference 2D face with those of the target face. Then, we employ the LTV model to factorize each of the two aligned face images to an illuminationdependent component and an illumination-invariant component. Finally, illumination transferring is achieved by replacing the illumination-dependent component of the target face by that of the reference face. (PDF)

Neuronal Spine Detection and Segmentation

Determining the relationship between the dendritic spine morphology and its functional properties is a fundamental while challenging problem in neurobiology research. In particular, how to accurately and automatically analyze meaningful structural information from a large microscopy image dataset is far away from being resolved. In this project, we present a framework to detect and segment neuronal spines. Especially, we propose a novel breaking-down and stitching-up algorithm to effectively separate touching spines. Our algorithm make full use of the local low-level geometric features, as well as the high-level geometric features of the dendrite structure. (PDF)

Neuronal Spine Tracking

Dendritic spines form postsynaptic contact sites in the central nervous system. The rapid and spontaneous morphology changes of spines have been widely observed by neurobiologists. Determining the relationship between dendritic spine morphology change and its functional properties such as memory learning is a fundamental yet challenging problem in neurobiology research. In this project, we propose a novel algorithm to track the morphology change of multiple spines simultaneously in time-lapse neuronal images based on non-rigid registration and integer programming. Our algorithm is capable of tracking a large number of neuronal spines in time-lapse confocal microscopy images. (PDF)

Publications

Reconstruction of the Neuromuscular Junction Connectome, Ranga Srinivasan, Qing Li, Xiaobo Zhou, Ju Lu, Jeff Lichtman, and Stephen T.C. Wong, Bioinformatics, Vol. 26 ISMB 2010, pages 64-70.

A Novel Surface-based Geometric Approach for 3D Dentritic Spline Detection From Multi-Photon Excitation Microscopy Images, Qing Li, Xiaobo Zhou, Zhigang Deng, Matthew Baron, Merilee A. Teylan, Yong Kim, and Stephen T.C. Wong, Proc. IEEE International Symposium on Biomedical Imaging (ISBI) 2009, Boston, MA, June 2009, pp. 1255-1258.

Online Three-Dimensional Dendritic Spines Morphological Classification Based on Semi-Supervised Learning, Peng Shi, Xiaobo Zhou, Qing Li, Matthew Baron, Merille A. Teylan, Yong Kim, and Stephen T. C. Wong, Proc. IEEE International Symposium on Biomedical Imaging (ISBI) 2009, Boston, MA, June 2009, pp. 1019-1022.

Perceptually Consistent Example-based Human Motion Retrieval, Zhigang Deng, Qin Gu, and Qing Li, Proc. ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (SI3D) 2009, Boston, MA, Feb 2009, pp. 191-198.

A Novel Visual System for Expressive Facial Motion Data Exploration, Tanasai Sucontphunt, Xiaoru Yuan, Qing Li, and Zhigang Deng, Proceeding of 2008 IEEE Pacific Visualization Symposium,Kyoto, Japan, March 5-7, 2008.

Online Motion Capture Marker Labeling for Multiple Interacting Articulated Targets, Qian Yu, Qing Li, and Zhigang Deng, Computer Graphics Forum (Proceedings of Eurographics 2007), Prague, Czech Republic, September 2007, pp. 477-483.