I am interested in modeling the statistics of images, from high-level representations of scenes and objects to low-level cues such as image gradients. Such models may be used for a range of applications within Computer Vision and Computational Photography. Below are brief descriptions of my research, along with links to pages giving more details.
The Internet is an incredibly rich resource of information that I am interested in using in conjunction with object recognition algorithms. The challenge is to design powerful algorithms that can scale to the billions of images on the web. My co-authors and I have explored methods that rely on massive amounts of data, as well as more traditional parametric models.
Computational Photography is an area at the convergence of Computer Graphics and Vision. My co-authors and I have used low-level statistical models of images in several applications that extend the capabilities of conventional cameras.
I am also interested in giving computers the ability to "see" just as humans do. A computer should be able to know where it is and what surrounds it just by looking. Today, cameras are ubiquitous but we lack the computational algorithms to process the images into more useful representations.