Saturday, March 16, 2013
Black & White HDR
http://thehdrimage.com/tag/black-white-hdr/
http://www.denzomag.com/2010/09/black-and-white-hdr-photography-amazing-examples/
Goal: Develop a math theory of B&W HDR image formation.
Friday, March 1, 2013
Image Super-resolution
Goal: Super resolution is one of the most important tasks in computer vision and computer graphics. Students will design an image super-resolution technique and study it’s theoretical property and/or a fast implementation of it.
Reference:
Radon Transform and Its Inverse Transform
Goal: The project aims to study the Radon transform for formation of MRI images.
References:
Image Matching Using Convex Optimization
Goal: The project studies approaches to recasting many classic image matching problems including, stereopsis, motion estimation, image registration and 3D volumetric matching as convex optimization problems that can be solved effectively using convex optimization methods.
Related Publications
- Solving Image Registration Problems Using Interior Point Methods. C. J. Taylor and A. Bhusnurmath. European Conference on Computer Vision, October 2008
- Graph Cuts via $\ell_1$ Norm Minimization. A. Bhusnurmath and C. J. Taylor. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol: 30, No: 10, Pgs: 1866-1871, October 2008
- Solving Stereo Matching Problems Using Interior Point Methods. A. Bhusnurmath and C. J. Taylor. Fourth International Symposium on 3D Data Processing, Visualization and Transmission, 3DPVT, Pgs: 321-329, June 2008
- Applying Convex Optimization Techniques to Energy Minimization Problems in Computer Vision. A. Bhusnurmath. PhD Thesis, Computer and Information Science Department, University of Pennsylvania, 2008
Iterative Closest Point Method
Goal: The project aims to determine numerical method to register between two point cloud images.
References:
Subscribe to:
Posts (Atom)
Volume Data Matching
Given two functions f(x,y,z) and g(x,y,z). One would like to determine a rigid body rotation to best match the zero level set of the functio...
-
( http://www.cis.upenn.edu/~cjtaylor/RESEARCH/projects/ImageMatching/ImageMatching.html ) Goal: The project studies approaches ...
-
Goal: This project investigates an extension of the classical concept of derivatives to shapes and topologies. We discuss concepts o...
-
Goal: Create the so-called depth map from either (i) a pair of left-right images obtained by two cameras with fixed location, or (ii) one ...