The Computer Graphics and Vision Group consists of researchers in image processing, computer vision, computer graphics, and machine learning. The primary goals of this group are the analysis, synthesis, understanding, and manipulation of visual data such as images, video sequences, and 3D geometric content.
Application areas span a broad range from entertainment to surveillance. The group is actively engaged in image and video editing and enhancement, special effects, 3D interactive content generation, sensor calibration, pattern recognition and object recognition. This research cluster includes the researchers from the Graphics & Image Technologies Laboratory as well as overlapping with researchers in the Learning and Adaptive Systems cluster.
- Computer animation
- Computer graphics
- Computer vision
- Geometric processing
- GPU computing/Parallel computing
- Image processing
- Information visualization
- Scientific visualization
- CS 419/519: ST/Computer Animation
- CS 450/550: Intro to Computer Graphics
- CS 553: Scientific Visualization
- CS 554: Geometric Modeling
- CS 551: Computer Graphics
- CS 556: Computer Vision
- CS 559: Selected Topics in Computer Vision
Visualization; GPU programming; high performance computer graphics; stereographics
Machine learning algorithms and applications; computer vision; segmentation-based object recognition and scene understanding; spatio-temporal cues in video
Computer graphics; visualization; geometry processing
Relationship between shape and biological function; design of interfaces for manipulating and annotating 3D images; artistic-based modeling and visualization
Object recognition; region / shape matching; texture; video object segmentation; stochastic image grammars
Modeling and simulation of biological and physical problems; mathematical optimization
Graphics & Image Technologies Laboratory
The IGVL supports research related to computer graphics, and vision. The lab currently consists of several high-end dual processor workstations with state-of-the-art 3D graphics acceleration hardware as well as disk arrays for efficient storage and access of video sequences. The lab is also equipped with cameras and display devices to support computer vision and projection display. The lab provides researchers with hardware and software to make progress in research areas including image and video editing and enhancement, special effects, 3D interactive interfaces, character animation, and 3D geometry representation.
Video Painting with Space-Time-Varying Style Parameters
( Todorovic, Zhang)
- Video painting system that accounts for the spatial support of objects in the images or video, and uses this information to specify style parameters and stroke orientation for painterly rendering.
- Object-based painterly rendering approach is characterized by style parameters that coherently vary in space and time.
- Spatiotemporal coherence of varying style parameters enables more artistic freedom.
Texel-based Texture Segmentation
- No assumptions about the pdf of texel properties.
- Both appearance and placement of the texels are allowed to be stochastic and correlated.
- New hierarchical, adaptive-bandwidth kernel to capture texel structural properties.