Research

Update: I will be joining the University of Maryland, College Park as an assistant professor of computer science in January.
I am an Intelligence Community postdoctoral research fellow in Gordon Wetzstein's Computational Imaging Lab. Previously, I was a PhD student in the Machine Learning, Digital Signal Processing, and Computational Imaging labs at Rice University, where I worked under the direction of professors Richard Baraniuk and Ashok Veeraraghavan. My research uses machine learning and statistical signal processing to develop data-driven solutions to extreme imaging problems.

My CV and Google Scholar profile.

Select Publications

Real-Time Unknown-View Tomography Using Recurrent Neural Networks with Applications to Keyhole Imaging
C. Metzler, G. Wetzstein. COSI 2020.

Deep S3PR: Simultaneous Source Separation and Phase Retrieval Using Deep Generative Models
C. Metzler, G. Wetzstein. Under Review.

Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path
C. Metzler, D. Lindell, G. Wetzstein. Under Review.

Deep Learning Techniques for Inverse Problems in Imaging
G. Ongie, A. Jalal, C. Metzler, R. Baraniuk, A. Dimakis, R. Willett. IEEE Journal on Selected Areas in Information Theory 2020.

Deep-inverse Correlography: Towards Real-Time High-Resolution Non-Line-of-Sight Imaging
C. Metzler, F. Heide, P. Rangarajan, M. Balaji, A. Viswanath, A. Veeraraghavan, and R. Baraniuk. Optica 2020.

Deep Optics for Single-shot High-dynamic-range Imaging
C. Metzler, H. Ikoma, Y. Peng, G. Wetzstein. CVPR 2020 (Oral).

Inverse Scattering via Transmission Matrices: Broadband Illumination and Fast Phase Retrieval Algorithms
M. Sharma, C. Metzler, S. Nagesh, R. Baraniuk, O. Cossairt, A. Veeraraghavan. IEEE Transactions on Computational Imaging 2019.

Unsupervised Learning with Stein's Unbiased Risk Estimator
C. Metzler, A. Mousavi, R. Heckel, R. Baraniuk. International Biomedical and Astronomical Signal Processing (BASP) Frontiers workshop 2019. Best contribution award.

prDeep: Robust Phase Retrieval with Flexible Deep Neural Networks
C. Metzler, P. Schniter, A. Veeraraghavan, R. Baraniuk. International Conference on Machine Learning 2018.

Imaging Through Extreme Scattering in Extended Dynamic Media
A. Kanaev, A. Watnik, D. Gardner, C. Metzler, K. Judd, P. Lebow, K. Novak, J. Lindle. Optics Letters 2018.

An Expectation-Maximization Approach to Tuning Generalized Vector Approximate Message Passing
C. Metzler, P. Schniter, R. Baraniuk. ICA/LVA Special Session on Advances in Phase Retrieval and Applications 2018.

Learned D-AMP: Principled Neural Network based Compressive Image Recovery
C. Metzler, A. Mousavi, R. Baraniuk. Neural Information Processing Systems 2017.

Coherent Inverse Scattering via Transmission Matrices: Efficient Phase Retrieval Algorithms and a Public Dataset
C. Metzler, M. Sharma, S. Nagesh, R. Baraniuk, O. Cossairt, A. Veeraraghavan. IEEE International Conference on Computational Photography 2017. ICCP best-paper runner-up.

BM3D-prGAMP: Compressive phase retrieval based on BM3D denoising
C. Metzler, A. Maleki, R. Baraniuk. IEEE International Conference on Image Processing 2016.

From Denoising to Compressed Sensing
C. Metzler, A. Maleki, R. Baraniuk. IEEE Transactions on Information Theory 2016.

Optimal recovery from compressive measurements via denoising-based approximate message passing
C. Metzler, A. Maleki, R. Baraniuk. International Conference on Sampling Theory and Applications 2015.

BM3D-AMP: A new image recovery algorithm based on BM3D denoising
C. Metzler, A. Maleki, R. Baraniuk. IEEE International Conference on Image Processing 2015. ICIP "Top 10%" paper.

Talks

prDeep: Robust Phase Retrieval with a Flexible Deep Network
Talk at ICML 2018.

Imaging Through Multiple Scattering Media Using Phase Retrieval
Invited talk at LVA/ICA 2018 Special Session on Phase Retrieval and Applications.

Unsupervised Learning with Stein's Unbiased Risk Estimator: A Practical Approach to Universal Compressive Sensing
Talk at SIAM IS-18 Minisymposium on Computational and Compressive Imaging Technologies and Applications.

Data Driven Computational Imaging: Improved Imaging Through Scattering Media with Visible Light
Invited talk at Stanford Center for Image System Engineering 2018.

Phase Retrieval: Fast, Robust, and Data-driven Algorithms for Computational Imaging
Invited talk at SPIE Photonics West QPI IV 2018.

Unrolling: A Principled Method to Develop Deep Neural Networks
Talk at Rice Geo-Mathematical Imaging Group Project Review 2017.

Coherent Inverse Scattering via Transmission Matrices: Efficient Phase Retrieval Algorithms and a Public Dataset
Talk at ICCP 2017.

BM3D-prGAMP: Compressive Phase Retrieval Based on BM3D Denoising
Talk at ICME MM-SPARSE workshop 2016.

Connecting Bayesian and Denoising-based Compressed Sensing
Invited talk at Asilomar 2015.

BM3D-AMP: A New Image Recovery Algorithm Based on BM3D Denoising
Talk at ICIP 2015.

Software

Learned D-AMP, D-AMP, & D-prGAMP Toolbox: Neural networks and algorithms for compressive sensing and compressive phase retrieval. Includes code to train with SURE loss, instead of MSE.

Deep Simultaneous Source Separation and Phase Retrieval: Code to solve S3PR using deep generative models.

Deep-Inverse Correlography: Neural networks for imaging around corners using phase retrieval.

prDeep: A neural-network-based noise-robust phase retreival algorithm.

Datasets

Transmission Matrix Dataset: A public dataset for testing phase retrieval algorithms.

Biography

I received my BS, MS, and PhD, all in electrical and computer engineering, from Rice University in 2013, 2014, and 2019, respectively. My graduate and postdoctoral education has been supported by DoE IC, NSF GRF, DoD NDSEG, NASA TSGC, Texas Instruments, and Ken Kennedy Institute fellowship programs.

I have had six summer internships; one at the Naval Research Laboratory, two at Ball Aerospace, one at ViaSat, one at National Instruments, and one at the Technical University of Braunschweig. In high school I worked weekends and summers as an apprentice electrician.

I am an active member of the IEEE. I regularly review for the IEEE Transactions on Signal Processing, Information Theory, Image Processing, and Computational Imaging, in addition to several other journals and conferences.

Contact Info

My email address is cmetzler at stanford.edu.

My office is room 228 in the Packard Building.