Publications


Full Publications
  1. Michael Kellman, Kevin Zhang, Eric Markley, Jon Tamir, Emrah Bostan, Michael Lustig, and Laura Waller, "Memory-efficient learning for large-scale computational imaging," IEEE Transactions on Computational Imaging, October 2020, doi: 10.1109/TCI.2020.3025735.

  2. Emrah Bostan, Reinhard Heckel, Michael Chen, Michael Kellman, and Laura Waller, "Deep Phase Decoder: Self-calibrating phase microscopy with an untrained deep neural network," OSA Optica, January 2020, doi: 10.1364/OPTICA.389314.

  3. Michael Kellman, Emrah Bostan, Michael Chen, and Laura Waller, "Data-driven Design for Fourier Ptychographic Microscopy," IEEE International Conference on Computational Photography, May 2019, doi: 10.1109/ICCPHOT.2019.8747339.

  4. Michael Kellman, Emrah Bostan, Nicole Repina, and Laura Waller, "Physics-based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imaging," IEEE Transactions on Computational Imaging, March 2019, doi: 10.1109/TCI.2019.2905434.

  5. Michael Kellman, Michael Chen, Zachary Phillips, Michael Lustig, and Laura Waller, "Motion-resolved Quantitative Phase Imaging," Biomedical Optics Express, November 2018, doi: 10.1364/BOE.9.005456.

  6. Michael Kellman, Francois Rivest, Alina Pechacek, Lydia Sohn, and Michael Lustig, "Node-Pore Coded Coincidence Correction: Coulter Counters, Code Design, and Sparse Deconvolution," IEEE Sensors Journal, April 2018, doi: 10.1109/JSEN.2018.2805865.


Conference Abstracts
  1. Michael Kellman, Eric Markley, Kevin Zhang, Jon Tamir, Emrah Bostan, Michael Lustig, and Laura Waller, "Memory-efficient learning for large-scale computational imaging," Computer Vision and Pattern Recognition: Computational Cameras and Displays, June 2020.

  2. Ruiming Cao, Michael Kellman, David Ren, and Laura Waller, "3D Differential Phase Contrast Microscopy with Axial Motion Deblurring," OSA Computational Optical Sensing and Imaging, June 2020.

  3. Kevin Zhang*, Michael Kellman*, Jon Tamir, Michael Lustig, and Laura Waller, "Memory-efficient learning for unrolled 3D MRI reconstructions," ISMRM Data sampling and reconstruction workshop, Sedona, AZ, January 2020.

  4. Michael Kellman, Jon Tamir, Emrah Bostan, Michael Lustig, and Laura Waller, "Memory-efficient learning for large-scale computational imaging," NeurIPS workshop deep inverse, Vancouver, Canada, December 2019.

  5. Michael Kellman, Emrah Bostan, Michael Lustig, and Laura Waller, "Data-driven experimental design for computational imaging," SPIE PW Quantitative Phase VI, San Francisco, CA, February 2020.

  6. Regina Eckert, Michael Kellman, and Laura Waller, "Physics-based learning for measurement diversity in 3D refractive index microscopy," SPIE PW Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XXVII, San Francisco, CA, February 2020.

  7. Kevin Zhang, Michael Kellman, Emrah Bostan, and Laura Waller, "3D fluorescence deconvolution with deep priors," SPIE PW Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XXVII, San Francisco, CA, February 2020.

  8. Emrah Bostan, Michael Kellman, and Laura Waller, "Learning-Optimized Imaging Models for Optical Phase Retrieval," International BASP Frontiers workshop, Villars-sur-Ollon, Switzerland, February 2019.

  9. Michael Kellman, Emrah Bostan, Nicole Repina, Michael Lustig, and Laura Waller, "Physics-based Learned Design: Optimized Illumination for Quantitative Phase Imaging," SPIE PW Quantitative Phase V, San Francisco, CA, January 2019.

  10. Michael Kellman, Zachary Phillips, Michael Chen, Michael Lustig, and Laura Waller, "Motion Resolved Quantitative Phase Imaging," IEEE International Conference on Computational Photography, Pittsburgh, PA, April 2018.

  11. Michael Kellman, Zachary Phillips, David Ren, Michael Lustig, and Laura Waller, "Motion Resolved Quantitative Phase Imaging," SPIE DCS Computational Imaging III, Orlando, FL, April 2018. doi: 10.1117/12.2300100.

  12. Michael Kellman, Francois Rivest, Alina Pechacek, Lydia Sohn, and Michael Lustig"Barker-Coded Node-Pore Resistive Pulse Sensing with Built-in Coincidence Correction," IEEE ICASSP Annual Meeting, New Orleans, LA, April 2017, doi: 10.1109/ICASSP.2017.7952317.


Theses & Technical Reports
  1. Michael Kellman "Physics-based Learning for Large-scale Computational Imaging," UC Berkeley EECS PhD Dissertation, August 2020, UCB/EECS-2020-167.

  2. Michael Kellman, Michael Lustig, and Laura Waller, "How to do Physics-based Learning," Arxiv, May 2020, doi: arXiv:2005.13531.

  3. Michael Kellman and Michael Lustig, "Node-Pore Coded Coincidence Correcting Microfluidic Channel Framework: Code Design and Sparse Deconvolution," UC Berkeley EECS Master Thesis, December 2017, UCB/EECS-2017-213.


Invited Talks
  1. Data-driven Design for Computational Imaging, Berkeley Artificial Intelligence Research Seminar, UC Berkeley, September 2019.

  2. Data-driven Design for Computational Imaging, ImageXd, UC Berkeley, September 2019.

  3. Data-driven Design for Computational Imaging, Statistics and Geonomics Seminar, UC Berkeley, April 2019.

  4. Physics-based Machine Learning, Berkeley Center on Computational Imaging Seminar, UC Berkeley, November 2018.

  5. Node-Pore Sensing: Microfluidics and Coding, Berkeley Center on Computational Imaging Seminar, UC Berkeley, February 2017.


Copyright 2019 Michael Kellman. All rights reserved.
Template borrowed from Jon Barron.

URL Counter