Recent Changes - Search:

My Research

Teaching

Main / Practice

Michael Gleicher
Professor
Department of Computer Sciences
University of Wisconsin, Madison
1210 West Dayton St.
Madison, WI 53706

gleicher@cs.wisc.edu
Office: 6385 Computer Sciences Building
Phone: 608-263-2874, Fax: 608-262-9777

Office Hours: Summer 09: By Appointment

I am a professor working in Computer Graphics and related areas (visulation, multimedia, animation, vision, ...). A brief biography will tell you how I got here. You can see a reasonably current CV, but you probably are looking for select publications (papers, videos, talks by project), or a more complete list of papers, talks, or videos in data order. I'l try to keep a list of project descriptions.

On this page: things I'm working on, teaching, recent papers.

This fall I will teach CS559 Computer Graphics.

I do External (Ph.D. Minor) Advising. If you need this, please come by my office hours - but check the guidebook rules first. I am not on UGAC anymore, so I cannot officially do undergraduate advising.

You might be interested in my grad school FAQ. Come and talk to me if you're interested in computer graphics or related topics.

If you're interested in joining our group, come talk to me! If you aren't a student at Wisconsin yet, please look at my grad school FAQ, particularly the last few questions.

Some things that I am working on these days


Abstracting Molecular Surfaces and Motion
The shapes and motions of large molecules (Proteins) are very

important, but very complicated. We are trying to find concise ways to describe them to make it easier to look at them visually, as well as to analyze them automatically. This includes novel visualization and collaboration tools, as well as automatic matching tools that work directly on the shape and physical property distributions.

Example projects: Molecular Surface Abstraction, Surface Descriptors, Depicting Molecular Flexibility, Multi-User Molecular Visualization
Molecular Motion with Aaron Bryden and George Phillips
We are trying to build better tools for understand the flexibility and motion of protein molecules. We're using coarse-grained models (e.g. normal mode analysis) and finding new ways to make these analyses useful.
Example Projects: Static depiction of motion, Normal Mode Explorer


Visualizing Comparisons
Increasingly, visualization needs to help people make comparisons between things in increasingly large data sets. In the past, visualization has focused on helping with particular types of objects: volumes, graphs, molecules, etc. In contast, the Visual Comparisons project tries to understand the general principles that apply no matter what is being compared. We are working with several domain collaborators to explore case studies of comparison to inform the general principles.
Current domain collaborations include Educational Science (comparing epistemic frames), Genetics (comparing whole genome alignments), Structural biology (protein shapes and motions), Literary Scholarship (statistical analysis of text corpora), and Virology (understanding virus evolution). We also collaborate with perception experts to better understand the mechanisms in interpreting images.
Example Projects: Splatterplots, Tagged Text Collections, Whole Genome Sequence Overviews, Comparing Epistemic Frames, Visualizing Virus Evolution, Explaining High-Dimensional Groups


Re-thinking Photography and Videography
Digital photography (and videography) has changed the world: it is easy (and cheap) to take lots of pictures and video, to share them with others, and to change them. This means its easy to get lots of bad pictures: good pictures (and video) still takes work.

Our goal is to make it easier for people to have useable images and video. For example, we have developed methods for improving pictures and video as a post-process (e.g. removing shadows and stabilizing video). We have also worked on adapting imagery for use in new settings (e.g. image and video retargeting or automatic video editing) and making use of large image collections (e.g. intestingness detection or panorama finding). In the future, we hope to put these elements together to make systems that help people make effective use of large collections of images and videos.

Example projects: Warp-Based Video Stabilization, Re-Cinematography, 3D Stabilization, Image and Video Retargeting, Panorama finding
Multimedia Database Usage with Feng Liu
We are developing ways to make use of collections of images and videos - both personal collections, as well as large internet databases. For example, we have created tools for finding panoramic images in YouTube collections.
Example Projects: Video frame interest, Panorama finding


Animating Communicative Characters
We are working on better ways to synthesize human motions to make animated characters (both on screen and robots) that are better able to communicate. Generally, we focus on trying to make use of collections of examples (such as motion capture) to build models that allow us to generate novel movements, or to define models of communicative motions.
Example Projects: Simulating Gaze Behaviors, Parametric Motion Controllers
Other Stuff
I have a bad case of Academic Attention Defecit Disorder, so I am always interested in other things - especially if they involve pictures, geometry, or motion.

Teaching

In the Fall, I teach CS559 Computer Graphics. You can find the web pages for the versions in 2009, 2008, 2007, 2006, 2005, and if you're really curious, even older versions of the course page are still on the Graphics Group Courses Page.

In the Spring, I teach some more advanced course. In Spring 2010 I will teach CS679 Computer Games Technologies (see the 2008 or 2007 versions of the class). In the Spring of 2009, I taught an Advanced Graphics class. In the past, I taught CS777 Computer Animation (2006, 2004, 2003, and . I am not sure when (or if) this class will be taught again.

You can find other information on graphics group classes on the Graphics Group Courses Page.

Recent Papers

I try to keep the complete list available here. Here are some recent ones:

  • IEEE Trans MM 09: Image Retargeting Using Mesh Parametrization w/Guo et al
  • Vis 09: Multiscale Surface Descriptors w/Cipriano and Phillips
  • SIGGRAPH 09: Content-Preserving Warps for 3D Video Stabilization w/Liu, Jin, and Agarwala
  • IJCAI 09: Using Web Photos for Measuring Video Frame Interestingness w/Liu and Niu
  • CVPR 09: Learning color and locality cues for moving object detection and segmentation w/Liu
  • CGF 09: Visual-Quality Optimizing Super Resolution w/Liu et al
  • ACM TOMCCAP 08: Re-Cinematography: Improving the camerawork of casual video w/Liu
  • Vis 08: Text Scaffolds for Effective Surface Labeling w/Cipriano
  • ECCV 08: Texture-Consistent Shadow Removal w/Liu
  • Multimedia 08: Discovering Panoramas in Web Videos w/Liu and Hu
  • Multimedia 08: Noisy video super-resolution w/Liu et al
  • SCA 08: Staggered Poses: A Character Motion Representation for Detail–Preserving Editing of Pose and Coordinated Timing w/Coleman et al
  • MIG 08: More Motion Capture in Games — Can We Make Example-Based Approaches Scale?
History - Print - Recent Changes - Search
Page last modified on July 16, 2009, at 11:52 AM