RI | People | Srinivasa G Narasimhan

Text only version of this site

Srinivasa G Narasimhan
Assistant Professor

Email address: srinivas@cs.cmu.edu

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

For more information, see my personal homepage.

Jump to: Biography | Research interests | Keywords | Labs & groups | Projects | Publications

Biography

Srinivasa Narasimhan is an Assistant Professor in the Robotics Institute at Carnegie Mellon University. He received his Masters and Doctoral degrees in Computer Science from Columbia University in December 2000 and 2003 respectively. From January 2004 to July 2004, he was a post doctoral research scientist at Columbia University. His research interests are in the fields of Computer Vision and Computer Graphics. Primarily, he is interested in the development of physics-based models and algorithms for understanding and rendering complex scene appearance. His paper on modeling and removing atmospheric effects from images has received the Best Paper Honorable Mention award at the 2000 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). He received the NSF CAREER award in January 2007.

Research interests

My research focuses on the physics of computer vision and computer graphics. My projects highlight three main aspects of my research - the mathematical modeling of the interactions of light with materials and the atmosphere; the design of novel cameras with higher resolution in space, color and intensity; and the development of algorithms for rendering and interpreting scene appearance. My research is motivated by applications in a wide range of fields including robotics, digital entertainment, remote sensing and underwater imaging.

My research projects.

Research interest keywords

computational sensors, computer graphics, computer vision, image processing, and optics

Current Labs & Groups

Computer Graphics Lab - Modeling, animation, and rendering of 3-D scenes

Current Projects

Coplanar Shadowgrams for Acquiring Visual Hulls of Intricate Objects - We present a practical approach to shape-from-silhouettes using a novel technique called coplanar shadowgram imaging that allows us to use dozens to even hundreds of views for visual hull reconstruction.

Recent publications [View all 30 publications]

• Temporal Dithering of Illumination for Fast Active Vision
  S.G. Narasimhan, S.J. Koppal, and S. Yamazaki
  European Conference on Computer Vision, October, 2008.

• Camera parameters estimation from hand-labelled sun positions in image sequences
  J. Lalonde, S.G. Narasimhan, and A.A. Efros
  tech. report CMU-RI-TR-08-32, Robotics Institute, Carnegie Mellon University, July, 2008. [Abstract]
  Download: pdf [836 KB] copyrighted

• On Controlling Light Transport in Poor Visibility Environments
  M. Gupta, S.G. Narasimhan, and Y.Y. Schechner
  Proceedings IEEE CVPR 2008, June, 2008. [Abstract]
  Download: pdf [2907 KB] copyrighted

• Appearance Derivatives for Iso-normal Clustering of Scenes
  S.J. Koppal and S.G. Narasimhan
  Pattern Analysis and Machine Intelligence, May, 2008.

• What does the sky tell us about the camera?
  J. Lalonde, S.G. Narasimhan, and A.A. Efros
  European Conference on Computer Vision, 2008. [Abstract]
  Download: pdf [2895 KB] copyrighted

• Coplanar Shadowgrams for Acquiring Visual Hulls of Intricate Objects
  S. Yamazaki, S.G. Narasimhan, S. Baker, and T. Kanade
  International Conference on Computer Vision (ICCV), October, 2007. [Abstract]
  Download: pdf [9014 KB] copyrighted

• Novel Depth Cues from Uncalibrated Near-field Lighting
  S.J. Koppal and S.G. Narasimhan
  IEEE International Conference on Computer Vision (ICCV), October, 2007.

• Shape-from-Shading under Near Point Lighting and Partial views for Orthopedic Endoscopy
  C. Wu, S.G. Narasimhan, and B. Jaramaz
  Workshop on Photometric Analysis For Computer Vision (PACV 2007), October, 2007. [Abstract]
  Download: pdf [2683 KB] copyrighted

• Legendre Fluids: A Unified Framework for Analytic Reduced Space Modeling and Rendering of Participating Media
  M. Gupta and S.G. Narasimhan
  Eurographics/ ACM SIGGRAPH Symposium on Computer Animation (2007), August, 2007. [Abstract]
  Download: pdf [1954 KB] copyrighted

• On Using Shadowgrams for Visual Hull Reconstruction
  S. Yamazaki, S.G. Narasimhan, S. Baker, and T. Kanade
  tech. report CMU-RI-TR-07-29, Robotics Institute, Carnegie Mellon University, August, 2007. [Abstract]
  Download: pdf [15573 KB] copyrighted