Kaushik Mitra

Postdoctoral Research Associate, ECE
Rice University
office. Duncan 2050
email. kaushik .dot. mitra -at- rice .dot. edu

Brief bio

I am a postdoctoral researcher in the Electrical and Computer Engineering department of Rice University. I am working under the supervision of Prof. Ashok Veeraraghavan in the Computational Camera Design lab. Before coming to Rice University, I did my Phd in the Electrical and Computer Engineering department at University of Maryland, College Park under the supervision of Prof. Rama Chellappa. My areas of research interests are in computational imaging, computer vision and machine learning. Currently, I am looking for an academic or research lab position in India or USA.


Traditionally, imaging/camera design and imaging inference (image processing, computer vision) have been done independently. However, by jointly designing the imaging optics and inference algorithms, we can significantly enhance the performance of conventional cameras. This is the philosophy behind the fast evolving field of Computational Imaging (CI). Examples of CI includes light field cameras, extended-depth-of-field cameras, motion deblurring cameras and so on. My research focuses on the following themes:

  • Develop theory to explore the performance limits of CI systems

  • Develop novel CI systems

  • Explore the promise of data-driven signal models in CI and computer vision

Theory for computational imaging

Framework for analysis of CI systems

Data-driven design for CI systems
ICCP 2014

Denoise or deblur: Parameter optimization for imaging systems
SPIE Electronic Imaging, 2014

Analyzing computational imaging systems
SPIE Newsroom, 2013

Novel CI systems and processing algorithms

"Improving resolution of light field using hybrid imagingdesign"
ICCP 2014

Compressive epsilon photography

A common framework for light field processing
CVPR Workshop 2012

Towards compressive camera networks
IEEE Computer 2014

Machine learning for computer vision

Missing data matrix factorization
NIPS 2010

Analysis of sparsity based robust regressionalgorihms

Robust regression using sparse learning techniques

Robust RVM regression using sparse outlier model
CVPR 2010

Computer vision (Face recognition and SfM)

Blur and illumination robust face recognition

Recognition of motion blurred faces
Book chapter in Motion Deblurring, CUP, 2014

Projective bundle adjustment using L-infty norm

Webpage credits

This webpage is modeled after Aswin's webpage.