Research

I am a computer science graduate student at Carnegie Mellon University studying computational and biological vision. I am interested in the statistics of natural scenes and the use of these statistics to help infer scene properties from images. My current work is the inference of 3D shape from single images. Most existing approaches to shape inference work by starting with theoretical, physics-based models of image formation and then inverting these models. Unfortunately, inverting the image formation process is highly underconstrained.  This forces us to revert to oversimplified models of image formation which may be unrealistic in natural scenes. Various assumptions about image formation parameters have to be made, such as Lambertian (matte) surface reflectance, uniform albedo, single point illumination, infinitely distant illumination, smooth 3D surface shape, the absence of shadows, the absence of interfacet reflection, and others. However, these assumptions are often violated in the real world, and this leads to poor generalization for these algorithms.

I believe that, in addition to clarifying the relative merit of these assumptions, a solid understanding of the statistics of natural scenes will uncover new, exploitable regularities in image formation that are not obvious from physical models. One of the earliest discoveries in our database was a direct anticorrelation between distance and brightness: darker image regions are more likely to be further away. That brighter objects appear closer was first observed by da Vinci. Our database provides the first evidence that this relationship holds in natural scenes. We believe that this trend is attributable to shadows: image regions that lie within object interiors, crevises, or concavities are farther from the observer than object exteriors, and the object interiors are more likely to lie in shadow. Additional exploitable statistical trends may result from regularities in the 3D shape of objects, regularities in their spatial relationships, regularities in the location and orientation of the observer, regularities in illumination conditions, etc. Despite the potential usefulness of statistical models, and the growing success of statistical methods in vision, few studies have been made into the statistical relationship between images and range images.

 

 Publications

Efficient Belief Propagation for Vision Using Linear Constraint Nodes
Brian Potetz
CVPR (IEEE Conference on Computer Vision and Pattern Recognition)  June 2007 (in press)
pdf
slides

bibtex




Neurophysiological Evidence of Cooperative Mechanisms for Stereo Computation
Jason Samonds, Brian Potetz, and Tai Sing Lee

NIPS (Advances in Neural Information Processing Systems) 19: 1201-1208, MIT Press, 2007
pdf

bibtex




Scaling Laws in Natural Scenes and the Inference of 3D Shape
Brian Potetz and Tai Sing Lee

NIPS (Advances in Neural Information Processing Systems) 18: 1089-1096, MIT Press, 2006

pdf
poster


bibtex

 

 

---

The Role of Spiking Nonlinearity in Contrast Gain Control and Information Transmission
Yuguo Yu, Brian Potetz, and Tai Sing Lee
Vision Research,  45(5): 583-592 (2005).

pdf


bibtex

 

 



Statistical Correlations Between 2D Images and 3D Structures in Natural Scenes
Brian Potetz and Tai Sing Lee

Journal of Optical Society of America, A. 20(7): 1292-1303 (2003).

pdf


bibtex




 Abstracts
Implications of neuronal interactions on disparity tuning in V1
Jason Samonds, Brian Potetz, and Tai Sing Lee
[Society for Neuroscience Abstract] (in press), 2007.

abstract






Disparity and Luminance Preferences are Correlated in Macaque V1,
Matching Natural Scene Statistics

Brian Potetz, Jason Samonds, and Tai Sing Lee
[Society for Neuroscience Abstract], 2006.

abstract
slides







Evidence of Cooperative and Competitive Mechanisms for Stereo Computation
in Macaque V1

Jason Samonds, Brian Potetz, and Tai Sing Lee
[Society for Neuroscience Abstract], 2006.

abstract







Cooperative Processing of Spatially Distributed Disparity Signals in Macaque V1
Jason M. Samonds, Brian Potetz, and Tai Sing Lee
[VSS Abstract] J. Vision 6(6):831a, 2006.
   
abstract
slides
  
bibtex