Computing That Serves

Building a Markov random field for super resolution


Thursday, November 4, 2004 - 10:00am


Marshall Tappen, MIT

A user who enlarges an image in a graphics package, such as Photoshop, often finds that while the image is larger, it also looks too smooth. This happens because traditional methods for enlarging images, such as bicubic interpolation, are unable to reconstruct the high-frequency image content necessary for a sharp image.  In this talk, I will describe how to build a statistical model of high-resolution images and show how this model can be used to estimate a high-resolution image from a lower-resolution input image.  To do so, I will show how to construct the model by using the choosing the proper state representation and clique potentials for a Markov Random Field.  I will also discuss the efficiency and efficacy of various algorithms for finding the high-resolution image, given a low-resolution input image.

Joint Work with Bryan C. Russell and William T. Freeman


Marshall Tappen is a PhD candidate in the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology.  He graduated with a BS in Computer Science from BYU in 2000 and received a SM degree in Electrical Engineering and Computer Science from MIT in 2002.  He is the recipient of the National Defense Science and Engineering Graduate (NDSEG) Fellowship.