H. Quynh Dinh: Home Page


H. Quynh Dinh, Ph.D. q (at) hqdinh.com CV . Publications . Grants

Research My research is in the areas of computer vision and graphics, with emphasis on shape reconstruction from point clouds, shape transformation, and geometric pattern matching. I also develop algorithms for shape and vector field pattern matching. The following summarizes my research projects.

Vector Field Pattern Analysis
	Analyzing vector fields impacts a diverse range of industries, including computational fluid dynamics (CFD), ocean engineering, medical imaging, and video and satellite imaging analysis among many others. We introduce algorithms for detecting local and global patterns in vector fields by capturing the statistics of the vector field in distributions that are then quantitatively compared for pattern detection. We show that global distributions are capable of distinguishing between vector fields of varying complexity and can be used to quantitatively compare similar fields. To record local statistics, we adapt the spin-image representation for surface points to vector fields (shape contexts and other data structures can be similarly adapted). Local distributions are used to track points through vector fields with the ultimate goal of identifying the source of turbulent flow, a problem important to automotive and ocean engineers. In automotive engine design, a turbulent-free flow through the combustion chamber leads to optimal mixing of fuel and air and a more efficient combustion process.
Publications: L. Xu, H.Q. Dinh, E. Zhang, Z. Lin, and R.S. Laramee. "A Distribution-Based Approach to Tracking Points in Velocity Vector Fields", IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2009. PDF 538KB L. Xu and H.Q. Dinh. "A Local Descriptor for Finding Corresponding Points in Vector Fields", IAPR International Conference on Pattern Recognition (ICPR), Dec. 2008 PDF 1.4MB H.Q. Dinh and L. Xu. "Measuring the Similarity of Vector Fields Using Global Distributions", IAPR International Workshop on Structural and Syntactic Pattern Recognition (SSPR) in conjunction with ICPR, Dec. 2008 PDF 3.8MB Sponsor: H.Q. Dinh. "Detecting Patterns in Vector Fields", Honda Initiation Grant, Honda Research Institute, 2009-2010.

Analogical Search
Search technology has become a significant market force due to the enormous amount of data that is publicly available on the internet. Data stores will only increase as more people contribute to media sharing sites (e.g., Flickr and Youtube), and this data will not be text data but rather, pictures, videos, and music. We are working with digital artists to develop a Transderivational/Transmedia search engine that suggests analogies across different media forms (e.g., images and videos) in a content-based manner. We are studying how visual elements such as shape, texture, and tone affect perceptions of similarity in images. The goal is to develop pattern matching algorithms that emulate the perceptual process (e.g., comparing the tone or structures within images) by which artists gather media samples for multimedia installations.
	In working towards an analogical search engine, we focus on developing robust representations of geometric data and pattern matching within a single media form, including 3D shape matching and detecting patterns in vector fields derived from time-varying 2D and 3D datasets (see Vector Field Pattern Analysis above). For 3D shape matching, we develop a multi-resolution approach that generates a pyramid of geometric distributions to efficiently find corresponding points between 3D shapes.
Publications: V. Petite , H.Q. Dinh, and E. Fisher. "A User Study on Perceiving Analogies in Images", International Digital Media and Arts Association (iDMAa) Conference, 2008. PDF 177KB H.Q. Dinh and S. Kropac. "Multi-Resolution Spin-Images", Computer Vision and Pattern Recognition (CVPR), June 2006 PDF 1.3MB Sponsor: H.Q. Dinh and E. Fisher. "A Transderivational Search Engine for Creative Analogy Generation in Mixed-Media Design", National Science Foundation Creative IT Program, Award# IIS-0742440, 2007-2009.

Modeling Implicit Surfaces Composed of Radial Basis Functions

In the digital entertainment industry, building geometric content for movies, video games, and virtual worlds is labor-intensive, even with CAD tools. We address this problem by smoothly interpolating discrete, noisy surface data captured using consumer digital cameras. We develop an approach called volumetric regularization to generate an implicit surface composed of radial basis functions (RBF). Volumetric regularization uses energy-minimizing 3D RBFs to balance between data fitting and functional smoothness. Our method generates a 3D implicit surface that approximates the data, closes off holes in the data, and is locally detailed, yet globally smooth. To preserve sharp features, we non-uniformly scale the RBFs, resulting in anisotropic RBFs. Extensions to this work include evolving RBF parameters for segmenting images, interactive rendering and modeling of implicit surfaces on the GPU, and frequency-domain filtering and X-ray visualization of irregularly sampled volumes on the GPU. Filtering and zooming directly in frequency space leads to more accurate and efficient signal processing. By using anisotropic RBFs fitted to data through optimization techniques, we allow the inclusion of advanced data-sensitive constraints for feature preservation.
Publications: H.Q. Dinh, N. Neophytou, and K. Mueller. “Continuous FVR of Irregularly Sampled Data Using Gaussian RBFs”, poster at the IEEE Visualization Conference, 2009. PDF 477KB (extended version PDF 1.1MB) G. Slabaugh, H.Q. Dinh, and G. Unal. "A Variational Approach to the Evolution of Radial Basis Functions for Image Segmentation", Computer Vision and Pattern Recognition (CVPR), June 2007 PDF 419KB A. Corrigan and H.Q. Dinh. "Computing and Rendering Implicit Surfaces Composed of Radial Basis Functions on the GPU", locally published at the International Workshop on Volume Graphics, June 2005 PDF 548KB H.Q. Dinh, G. Turk, and G. Slabaugh. "Reconstructing Surfaces by Volumetric Regularization Using Radial Basis Functions", IEEE Transactions on Pattern Analysis and Machine Intelligence, October 2002 PDF 2.9MB H.Q. Dinh, G. Turk, and G. Slabaugh. "Reconstructing Surfaces Using Anisotropic Basis Functions", International Conference on Computer Vision (ICCV), 2001 PDF 1.3MB Sponsor: H.Q. Dinh, G. Turk, G. Slabaugh, and R. Schafer. "Automated Construction of Digital Models from Real Artifacts", GVU Seed Grant, 2000

Implicit Shape Transformation (Morphing)

We reconstruct 4D implicit functions from time-varying surface data to obtain a 3D shape transformation (morph). Implicit shape transformation algorithms can create morphs between objects of arbitrary topology. However, explicit correspondences are not generated, making the transfer of surface properties (e.g., texture) impossible. Using heat diffusion, we build an explicit parameterization for implicit functions. In 4D, a parameterization provides a mapping between transforming 3D shapes and enables the transfer of material properties (e.g., color) from one surface to the next.
	The observation of the evolution of a course of treatment can provide a powerful tool in understanding its efficacy. To visualize this, we produce animations allowing the visualization, as a function of time, of lesions in an organ. The animation produced is a morph describing how a source shape (pre-treatment) gradually deforms into a target shape (post-treatment). The morph is computed on the GPU, so both visualization of the volumes and morph generation are performed in real-time.
Publications: H.Q. Dinh, A. Yezzi, and G. Turk. "Texture Transfer During Shape Transformation", ACM Transactions on Graphics (TOG), Vol.24(2), April 2005 PDF 9.78MB B. M. Carvalho and H.Q. Dinh. "Visualization of Treatment Evolution Using Hardware-Accelerated Morphs", 13th Conf. on Medicine Meets Virtual Reality (MMVR), Jan. 2005 PDF 183KB

Thesis Advising
Edgardo Molina. "Panorama Generation for Stereoscopic Visualization of Large-scale Scenes", CUNY Graduate Center, 2015 (PhD committee member) Hadi Fadaifard. "Multiscale Feature Extraction and Matching with Applications to 3D Face Recognition and 2D Shape Warping", CUNY Graduate Center, 2011 (PhD committee member) Lucy Xu. "Detecting Patterns in Vector Fields", 2006 - 2009 (PhD adviser) Steven Kropac. "Comparing Vector Fields Using Topology Analysis", 2005 - 2009 (PhD adviser) Hongzhi Wang. "Computational Methods for Perceptual Organization and Recognition", Stevens Institute of Technology, 2008 (PhD committee member) Haitao Zhang. "Point-based Modeling for Effective Rendering", SUNY Stony Brook, 2007 (PhD committee member) Neophytos Neophytou, "A Generalized Framework for Interactive Volumetric Point-Based Rendering", SUNY Stony Brook, 2006 (PhD committee member)

College Courses Taught
CS 437 - Intro to Computer Graphics CS 537 - Intro to Computer Graphics (graduate level) CS 638 - Advance Computer Graphics (graduate level) CS 492 - Intro to Operating Systems CS 520 - Intro to Operating Systems for (graduate level)