Graphics enhanced version of this site

Photometric Limits on Computer Vision
This project is no longer active.

Head: Simon Baker
Contact: Simon Baker

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Associated center: VASC

There has been a great deal of work in the computer vision literature investigating what can and cannot be computed from certain sets of "feature point coorespondences." Another potentially limiting factor on computer vision algorithms is photometrics; the intensity values recorded by real cameras. For example, pixel intensity noise can impose limits on what can be computed. We are investigating some of the limits that are imposed on computer vision algorithms by imperfect or incomplete photometric information. In particular, we are investigating the limits of super-resolution and stereo.

Super-Resolution

We have analyzed the super-resolution reconstruction constrants and derived a sequence of results which all show that the constraints provide less and less useful information as the magnification factor increases. Although smoothness priors can help regularize the problem, we have shown that they cannot compensate fully for the lack of information in the discretized photometric signal.

Stereo

When is stereo unique and when is it inherently ambiguous? We have investigated this question and derived a concise characterization of when the stereo problem (given the entire light-field) has a unique solution and when there are multiple scenes that could have generated the same set of photometric measurements (the light-field.)

Name - Title <Email Address>
• Simon Baker - Adjunct Faculty (Adjunct)
• [Home] Takeo Kanade - U.A. and Helen Whitaker University Prof., RI/CS <tk@cs.cmu.edu>
• [Home] Terence Sim - PhD Student, ECE

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• When is the Shape of a Scene Unique Given its Light-Field: A Fundamental Theorem of 3D Vision?
  S. Baker, T. Sim, and T. Kanade
  IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 25, No. 1, January, 2003, pp. 100 - 109. [Abstract]
  Download: pdf [155 KB] copyrighted

• Limits on Super-Resolution and How to Break Them
  S. Baker and T. Kanade
  IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9, September, 2002, pp. 1167 - 1183. [Abstract]
  Download: pdf [998 KB], ps.gz [1892 KB] copyrighted

• A Characterization of Inherent Stereo Ambiguities
  S. Baker, T. Sim, and T. Kanade
  Proceedings of the 8th IEEE International Conference on Computer Vision (ICCV'01), Vancouver, British Columbia, July, 2001. [Abstract]
  Download: pdf [107 KB], ps.gz [67 KB] copyrighted

• A Fundamental Theorem of Stereo?
  S. Baker, T. Sim, and T. Kanade
  tech. report CMU-RI-TR-01-07, Robotics Institute, Carnegie Mellon University, June, 2001. [Abstract]
  Download: pdf [116 KB], ps.gz [75 KB] copyrighted

• Super-Resolution: Reconstruction or Recognition?
  S. Baker and T. Kanade
  IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing, IEEE, Baltimore, Maryland, June, 2001. [Abstract]
  Download: pdf [228 KB], ps.gz [317 KB] copyrighted

• Super-Resolution: Limits and Beyond
  S. Baker and T. Kanade
  Super-Resolution Imaging, S. Chaudhuri, ed., Kluwer Academic Press, 2001.
  Download: pdf [783 KB], ps.gz [1267 KB] copyrighted

• Limits on Super-Resolution and How to Break Them
  S. Baker and T. Kanade
  Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition, June, 2000. [Abstract]
  Download: pdf [328 KB], ps.gz [423 KB] copyrighted