THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Rahul Bhotika (Graduate Student )
UR > CS > Research > Vision > People > Rahul Bhotika

Contact:

Rahul Bhotika
CSB 723
Department of Computer Science
University of Rochester
Rochester, NY 14627

vox: (585) 275-1443
email: bhotika@cs.rochester.edu
home: http://www.cs.rochester.edu/~bhotika
vision: http://www.rochester.edu/research/vision/people/Rahul_Bhotika

About:

I am a PhD candidate in the Computer Science Department at the University of Rochester. My research interests lie at the intersection of computer vision, computer graphics and machine learning.

Research Interests:

My research interests lie at the intersection of computer vision, computer graphics, and machine learning. Specifically, I am interested in recovering models of the geometric (shape, reflectance, transparency) and dynamic (motion, deformation) properties of real-world scenes (humans, objects, environments) from images and video, and using these models for applications such as scene understanding, tracking, rendering, motion synthesis and transfer, among others. My current research (including my PhD thesis) focuses on the use of probabilistic frameworks and geometric constraints to recover 3D shape and motion from multiple images. Our goal is to (1) develop theoretically sound frameworks that properly characterize the ambiguities and uncertainty inherent to the 3D reconstruction problem and to (2) design practical and robust reconstruction algorithms with provable behavior that work in the presence of such ambiguities and uncertainty. For more information about recent projects, click here.

Projects:


Publications:

A Probabalistic Theory of Occupancy and Emptiness (Rahul Bhotika and David J. Fleet and Kiriakos N. Kutulakos )
Flexible Flow for 3D Non-Rigid Tracking and Shape Recovery (Mathew Brand and Rahul Bhotika)