KAUSHIK MITRA CURRENT POSITION. Assistant Professor at Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai.

Transcription

1 KAUSHIK MITRA School Address Department of Electrical Engineering Indian Institute of Technology Madras Chennai, TN, India Web: Contact: CURRENT POSITION Assistant Professor at Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai. RESEARCH INTERESTS My research interests are in computational imaging, computer vision and machine learning. By jointly designing the imaging optics and inference algorithms, computational imaging (CI) systems have demonstrated significant performance improvement over conventional cameras. 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 EDUCATION Ph.D., Electrical and Computer Engineering University of Maryland, College Park, MD July 2011 Master of Engineering (M.E.), Electrical Communication Engineering Indian Institute of Science, Bangalore, India Jan 2003 Bachelor of Technology (B.Tech.), Radiophysics and Electronics University of Calcutta, Kolkata, India Aug 2001 RESEARCH AND PROFESSIONAL EXPERIENCE Postdoctoral Research Associate Aug 2011 Nov 2014 Rice University, Houston, USA Recently, many CI systems have been proposed for tackling the problem of motion blurring (for example Flutter Shutter), focus blurring (for example coded aperture cameras and extended depth of field cameras), light field capture, etc. Given that there are so many CI systems, it is imperative to compare and characterize their performance. I proposed a framework for analysis of CI systems that characterizes the performance of the systems by taking into account the effect of optical coding, image prior and sensor noise (TPAMI 2014). I then used this framework to find optimal camera parameters for conventional camera (SPIE 2014) and to design optimal optical codes for CI systems (ICCP 2014). I am also interested in designing novel CI systems. Current light field cameras (such as Lytro) have very poor spatial resolution. I have proposed a hybrid imaging system, consisting of a standard light field camera and a high resolution conventional camera, to generate high resolution light fields (ICCP 2014). I have also proposed a general framework for light field processing tasks such as denoising and (angular and spatial) superresolution (CVPR workshop 2012). Recently, I have proposed compressive epsilon photography, a technique for achieving post-capture control of focus, iso, exposure and aperture in a traditional camera by acquiring a carefully selected set of images and computationally reconstructing images corresponding to other focus and aperture settings (SIGGRAPH, 2014).

2 Graduate Research Assistant Aug 2004 July 2011 University of Maryland, College Park, MD, USA I proposed robust and efficient machine learning algorithms for a large class of computer vision problems. Many computer vision problems can be formulated as learning problems such as regression and matrix factorization. However, because of variations due to viewpoint, occlusion, shadows, etc., the visual data suffers from significant outliers and missing data, and this makes the learning problems very challenging. Towards solving the problem of outliers, I have proposed robust regression algorithms, based on sparse regularization and Bayesian techniques, that can handle large amount of outliers (CVPR 2010, ICASSP 2010). I have performed analysis of the robust algorithms to provide estimates of the fraction of outliers in a dataset that the proposed algorithms can successfully handle (TSP 2013). Towards solving the problem of missing data in matrix factorization, I have formulated it as a low-rank semidefinite programming problem with the advantage that it can handle large-scale vision datasets (NIPS 2010). I have also worked in the traditional vision problems of Structure from Motion (SfM) and face recognition. In SfM I have proposed a scalable algorithm for projective bundle adjustment (ICVGIP 2008) and in face recognition I have proposed an algorithm to identify blurred and poorly illuminated faces (TIP 2013). Senior Software Engineer, Samsung India Software Operations Feb 2003 July 2004 I worked on the multimedia software (audio, video, streaming players) of the Samsung mobile phone platform. TEACHING EE2004 Digital Signal Processing, Spring EE6132 Deep Learning for Imaging (Advanced Topics in Signal Processing), Fall EE5177 Machine Learning for Computer Vision, Spring 2016 and Spring EE5176 Computational Photography, Fall 2015 and Fall JOURNAL PUBLICATIONS A. Dave, A. K. Vadathya, R. Subramanyam, R. Baburaj, K. Mitra, Solving Inverse Computational Imaging Problems using Deep Pixel-level Priors, under review in IEEE Transactions on Computational Imaging. J. Holloway, K. Mitra, S. Koppal, A. Veeraraghavan, Generalized Assorted Camera Arrays: Robust Cross-channel Registration and Applications, IEEE Transactions on Image Processing (TIP), vol. 24(3), March A. Ito, S. Tambe, K. Mitra, A. Sankaranarayanan, A. Veeraraghavan, Compressive Epsilon Photography for Post-Capture Control in Digital Imaging, ACM Trans. Graphics (TOG) / SIGGRAPH, vol. 33(4), July K. Mitra, O. Cossairt and A. Veeraraghavan, A Framework for Analysis of Computational Imaging Systems: Role of Signal Prior, Sensor Noise and Multiplexing, IEEE Transactions on Pattern Analysis and Machine Learning (TPAMI), vol. 36(10), Oct K. Mitra, A. Veeraraghavan, A. Sankaranarayanan and R. G. Baraniuk, Towards Compressive Camera Networks, IEEE Computer, vol. 47(5), May P. Vageeswaran, K. Mitra and R. Chellappa, Blur and Illumination Robust Face Recognition via Set-Theoretic Characterization, IEEE Transactions on Image Processing (TIP), vol. 22(4), April K. Mitra, A. Veeraraghavan and R. Chellappa, Analysis of Sparse Regularization Based Robust Regression Algorithms, IEEE Transactions on Signal Processing (TSP), 2013.

3 CONFERENCE PUBLICATIONS L. Boominathan, M. Maniparambil, H. Gupta, Rahul B.and K. Mitra, Phase retrieval for Fourier Ptychography under varying amount of measurements, British Machine Vision Conference, Sep 2018, Newcastle upon Tyne, UK. A. K. Vadathya, S. Cholleti, G. Ramajayam, V. Kanchana, K. Mitra, Learning light field reconstruction from a single coded image, Asian Conference on Pattern Recognition (ACPR), Nov 2017, Nanjing, China. S. A. Baby, B. Vinod, C. Chinni, K. Mitra, Dynamic Vision Sensors for Human Activity Recognition, Asian Conference on Pattern Recognition (ACPR), Nov 2017, Nanjing, China. D. C. Kavarthapu, K. Mitra, Hand Gesture Sequence Recognition using Inertial Motion Units(IMUs), Asian Conference on Pattern Recognition (ACPR), Nov 2017, Nanjing, China. A. Dave, A. K. Vadathya and K. Mitra, Compressive image recovery using recurrent generative model, IEEE International Conference on Image Processing (ICIP), Sep 2017, Beijing, China. P. Shedligeri, S. Mohan and K. Mitra, A data driven approach for coded aperture design for depth-map recovery, IEEE International Conference on Image Processing (ICIP), Sep 2017, Beijing, China. S. Honnungar, J. Holloway, A. K. Pediredla, A. Veeraraghavan and K. Mitra, Focal-sweep for large aperture time-of-flight cameras, IEEE International Conference on Image Processing (ICIP) R. Tadano, A. K. Pediredla, K. Mitra and A. Veeraraghavan, Spatial Phase-Sweep: Increasing temporal resolution of transient imaging using a light source array, IEEE International Conference on Image Processing (ICIP) S. Barua, K. Mitra and A. Veeraraghavan, Saliency guided wavelet compression for low-bitrate image and video coding, IEEE Global Conference on Signal and Information Processing (GlobalSIP) K. Mitra, O. Cossairt and A. Veeraraghavan, Can we Beat Hadamard Multiplexing? Data-driven Design and Analysis for Computational Imaging Systems, IEEE International Conference on Computational Photography (ICCP) V. Boominathan, K. Mitra and A. Veeraraghavan, Improving Resolution and Depth-of-Field of Light Field Cameras Using a Hybrid Imaging System, IEEE International Conference on Computational Photography (ICCP) K. Mitra, O. Cossairt and A. Veeraraghavan, To Denoise or Deblur: Parameter Optimization for Imaging Systems, SPIE Electronic Imaging O. Cossairt, A. Veeraraghavan, K. Mitra and M. Gupta, Performance Bounds for Computational Imaging, Imaging and Applied Optics Technical Papers, OSA O. Cossairt, K. Mitra and A. Veeraraghavan, Performance Limits for Computational Photography, International Workshop on Advanced Optical Imaging and Metrology, Springer, K. Mitra and A. Veeraraghavan, Light Field Denoising, Light Field Superresolution and Stereo Camera Based Refocussing using a GMM Light Field Patch Prior, CVPR Workshop on Computational Cameras and Displays, P. Thukral, K. Mitra and R. Chellappa, A Hierarchical Approach For Human Age Estimation, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) K. Mitra, S. Sheorey, R. Chellappa, Large-Scale Matrix Factorization with Missing Data under Additional Constraints, Advances in Neural Information Processing Systems (NIPS) K. Mitra, A. Veeraraghavan and R. Chellappa, Robust RVM Regression Using Sparse Outlier Model, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) K. Mitra, A. Veeraraghavan and R. Chellappa, Robust Regression Using Sparse Learning for High Dimensional Parameter Estimation Problem, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2010.

4 K. Mitra and R. Chellappa, A Scalable Projective Bundle Adjustment Algorithm using the L Norm, Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) BOOK CHAPTER K. Mitra, P. Vageeswaran and R. Chellappa, Recognition of Motion Blurred Faces, Motion Deblurring: Algorithms and Systems, Cambridge University Press, A. N. Rajagopalan and R. Chellappa (Editors), SELECTED TALKS Tackling Resolution Tradeoff in Computational Imaging, Keynote speaker at IEEE International Conference on Computer, Communication, and Signal Processing, SSN College of Engineering, Jan Computational Imaging, talk during Qualcomm Innovation Fellowship (QINF) day, Qualcomm India, Bangalore, July Getting in focus with computational imaging, Workshop at Image Sensors Europe, London, March 2015 Computer vision for advanced driver assistance systems, invited talk at Texas Instruments, Bangalore, Dec Signal Processing Meets Optics: Theory, Design and Inference for Computational Imaging, talk at various IITs such as Kanpur, Delhi, Bombay and Madras, April-May To Denoise or Deblur: Parameter Optimization for Imaging Systems, SPIE Electronic Imaging, San Francisco January Light Field Denoising, Light Field Superresolution and Stereo Camera Based Refocussing using a GMM Light Field Patch Prior, CVPR Workshop on Computational Cameras and Displays, Providence, Rhode Island, June Handling Outliers and Missing Data in Statistical Data Models, talk at Electronics and Communication Sciences Unit (ECSU), Indian Statistical Institute (ISI), Kolkata, India,January Fitting Models to Data: Handling Outliers and Missing Data, talk at Mitsubishi Electric Research Laboratories (MERL), Cambridge, July Fitting Models to Data: Handling Outliers and Missing Data, talk at MIT Media Lab, Camera Culture Lab, July 2010 Scalable Bayesian Robust Regression for High Dimensional Applications, talk at Statistics Department, Florida State University, March A Scalable Projective Bundle Adjustment Algorithm using the L Norm, talk at the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), Bhubaneswar, India, December AWARDS Our team consisting of 2 graduate students and myself won the prestigious Qualcomm Innovation Fellowship Award 2016 from IIT Madras. Graduate student fellowship at University of Maryland ( ). Ranked Second in M.E. (IISc, Bangalore). All India Rank Second in ECE, Graduate Apitute Test in Engineering (GATE) Ranked first in B.Tech. (University of Calcutta) 2001.

5 PROFESSIONAL SERVICE One of the Technical Program Committee Chairs for National Conference on Communications (NCC) 2017 held in IIT Madras. Area Chair for Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), Guwahati Reviewer for IEEE Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing, IEEE Transactions on Computational Imaging, IEEE Journal of Selected Topics in Signal Processing. Reviewer for ICCP 2016, 2017; SIGGRAPH 2016, 2017; CVPR 2016, 2017; ICCV 2015, 2017.