Jan Neumann

What's New:

• 01-20-04: I added links to my curriculum vitae and research and teaching statements.
• 11-03-03: Check out what the New Scientist reports on the research of our group. Our work developing better "eyes" for robots is also the topic of a Reuters article.
• 10-05-03 The final versions of my CVPR and ICCV 2003 papers are available on my publication page.

Main Menu

Personal Info:

Office: AVW 4470 :: Tel.: 301 405 1762 :: jneumann at cfar.umd.edu

Research (Research statement):

I am interested in the geometry and statistics of visual space-time, i.e. representations of 3D shape and movement that can be extracted from images. This work has applications in many areas of computer vision and graphics, for example it lead to

	•  a better understanding of the geometric structure of the space of light rays ,
	•  the design of novel image sensors, and the development of new vision algorithms that utilize the special properties of these new sensors (example 3D structure from motion),
	•  new approaches to capture and analyze the 3D shape and motion of non-rigidly moving humans and objects,
	•  and methods rooted in geometry and statistics to track independently moving objects in videos.

More detailed information about my research can be found on my research overview page, my research statement and in my publications.

Selected publications that best represent my work

1. Plenoptic video geometry.

   Jan Neumann and Cornelia Fermüller. Visual Computer, Volume 19, Number 6, Pages 395-404, October 2003.
   (Link to published paper) (Link to preprint)

2. Eye Design in the Plenoptic Space of Light Rays

   Jan Neumann, Cornelia Fermüller, and Yiannis Aloimonos. Ninth IEEE International Conference on Computer Vision, Volume 2, pages 1160-1167, Nice, France, October 13-16 2003.
   (Link to published paper) (Link to preprint)

3. Polydioptric Camera Design and 3D Motion Estimation

   Jan Neumann, Cornelia Fermüller, and Yiannis Aloimonos. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, pages 294-301, Madison, Wisconsin, June 16-22, 2003.
   (Link to published paper) (Link to preprint)

4. Spatio-temporal stereo using multi-resolution subdivision surfaces.

   Jan Neumann and Yiannis Aloimonos.
   International Journal of Computer Vision, 47(1/2/3):181-193, 2002.
   (Link to published paper) (Link to preprint)

• A link to my other publications

PhD Thesis (expected date of completion, May 2004):

My thesis is inspired by sensory ecology, a discipline that studies the relationship between the behavior of an organism, the information it extracts to control its behavior and the environment in which it exists. I am especially intrigued by its description how the interplay between physical and environmental constraints governs the evolution of the sensors of an organism. In my thesis I attempt to capture the principles that govern the natural evolution of biological vision sensors in a mathematical framework, and then apply them to the design of artificial vision sensors. The mathematical framework that I am developing in my thesis can be of great help in this process by enabling the optimal design and construction of large camera networks and small insect-eye like sensors in a unified mathematical framework. This approach is validated by the prototypes that I am implementing at the moment. I believe that task-specific camera design has great potential to alter the way we sense our environment especially with the advent of optical nano-technology around the corner which will offer new opportunities to design revolutionarily different cameras that sample the space of light rays in ways unimaginable to us today. For more information please see the prospectus of my thesis (PDF, 3.3MB).

Teaching:

In Fall 2002 I cotaught the class CMSC828Z - 3D Photography and Inverse Rendering. In this class we talked about how computer vision and computer graphics can mutually benefit from eachother since one can be interpreted as the inverse problem of the other. Specifically, I talked about how computer graphics transforms our models of the world into images (Rendering and Animation), and how computer vision allows us to infer models of the world based on these images (3D Photography and Motion Capture). More information about my teaching philosophy can be found in my teaching statement.

"The reasonable man adapts himself to the world; the unreasonable one persists in trying to adapt the world to himself. Therefore all progress depends on the unreasonable man." G.B. Shaw