/home

/academics

/resume

/personal

/contact



Santosh Kumar Divvala

Hello! I am a ((n+1)-2007)th year doctoral student at the Robotics Institute, Carnegie Mellon University. My interests are in Computer Vision, specifically the Scene/Image Understanding problem. My approach to this problem takes a Machine Learning perspective so as to leverage today's Internet-scale image & video databases. The results of my research apply to Robotics (helping robots better 'interpret' the world around them) & to Computational Photography (enhancing the way we humans relish our photo collections).

At the RI, I work with Martial Hebert and Alyosha Efros.

Before joining the RI, I did my Undergrad and Masters (Dual Degree) at the Center for Visual Information Technology, IIIT Hyderabad, India. At IIIT-H, I had worked with C V Jawahar and P J Narayanan.

This Fall'09 semester, I will be a visiting student researcher at ENS/INRIA Paris as part of the WILLOW Research team!

email:




   

Projects/Publications

An Empirical Study of Context in Object Detection

[Project page] [Paper] [Presentation] [Poster]

A Unified Approach for Detection, Classification and Segmentation

[Project page] [Paper] [Presentation]

A Space-Carving Approach to Surface Estimation

[Project page] [Paper] [Presentation] [Poster]

Can Similar Scenes help Surface Layout Estimation?

[Project page] [Paper] [Presentation] [Talk Video]

Autonomous Image-based Exploration for Mobile Robot Navigation

[Project page] [Presentation] [Video]

Visual Servoing in Unconventional Environments

[Project page] [Presentation]