I work on computational imaging for science. In particular, I develop methods for carefully using priors, such as AI and scientific knowledge, to push the limits of conventional optics.
I'm currently a Postdoctoral Fellow at MIT and IAIFI, working with Prof. Bill Freeman. I obtained my PhD from Caltech, where I was advised by Prof. Katie Bouman. Previously, I graduated from Princeton University summa cum laude, with a major in Computer Science and minor in Statistics & Machine Learning.
I am currently on the academic job market for tenure-track faculty positions.
News
Oct 2025 I led the IAIFI panel at the Boston Diffusion Day workshop.
Sep 2025 I joined MIT as a postdoc! Officially I am an NSF IAIFI Fellow and Tayebati Postdoctoral Fellow.
Jul 2025 I delivered a keynote at the ML4Astro workshop.
Jul 2025 I taught the EHT Black-Hole Imaging course at the ICCP Summer School. Click here for the course materials.
Jan 2025 Check out my article on Seeing Beyond the Blur with Generative AI in the ACM’s XRDS Magazine!
MoreOct 2025 I led the IAIFI panel at the Boston Diffusion Day workshop.
Sep 2025 I joined MIT as a postdoc! Officially I am an NSF IAIFI Fellow and Tayebati Postdoctoral Fellow.
Jul 2025 I delivered a keynote at the ML4Astro workshop.
Jul 2025 I taught the EHT Black-Hole Imaging course at the ICCP Summer School. Click here for the course materials.
Jan 2025 Check out my article on Seeing Beyond the Blur with Generative AI in the ACM’s XRDS Magazine!
Nov 2024 Presented an invited talk at the SCIEN seminar series at Stanford University.
Oct 2024 Presented an invited talk for the imaging reading group at Carnegie Mellon University.
Sep 2024 Presented an invited plenary talk at the Deep Learning for Inverse Problems workshop at DESY in Hamburg, Germany.
Aug 2024 Presented a lightning talk and poster at the Computational Imaging workshop hosted by the Institute for Mathematical and Statistical Innovation (IMSI) at the University of Chicago.
Aug 2023 Excited to co-organize the Quo Vadis, Computer Vision? workshop at ICCV 2023 with Prof. Georgia Gkioxari!
Jul 2023 Excited to speak at the Astro + Imaging Workshop at Northwestern, organized by Profs. Emma Alexander and Jason Wang!
Jul 2023 Presented a Spotlight poster at ICCP 2023
Jul 2023 Paper about score-based priors accepted to ICCV 2023
Jun 2022 Selected as a Best Paper Finalist at CVPR 2022!
Mar 2022 Visual Vibration Tomography accepted to CVPR 2022 as an Oral
May 2021 Awarded the Best Poster Award at ICCP 2021 for Visual Vibration Tomography!
Mar 2020 Awarded the NSF Graduate Research Fellowship!
Oct 2019 Excited to start my PhD at Caltech, advised by Prof. Katie Bouman!
LessHighlighted Publications
Dynamic Black-hole Emission Tomography with Physics-informed Neural Fields
Berthy T. Feng, Andrew A. Chael, David Bromley, Aviad Levis, William T. Freeman, Katherine L. Bouman
In submission, 2026
Webpage coming soon
Visual Surface Wave Elastography: Revealing Subsurface Physical Properties via Visible Surface Waves
Alexander C. Ogren*, Berthy T. Feng*, Jihoon Ahn, Katherine L. Bouman, Chiara Daraio
ICCV, 2025
Paper Code
Neural Approximate Mirror Maps for Constrained Diffusion Models
Berthy T. Feng, Ricardo Baptista, Katherine L. Bouman
ICLR, 2025
Paper Code
Event-horizon-scale Imaging of M87* under Different Assumptions via Deep Generative Image Priors
Berthy T. Feng, Katherine L. Bouman, William T. Freeman
The Astrophysical Journal (ApJ), 2024
Webpage Paper
Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior
Berthy T. Feng, Katherine L. Bouman
Transactions on Machine Learning Research (TMLR), 2024
Webpage Paper Code
Score-Based Diffusion Models as Principled Priors for Inverse Imaging
Berthy T. Feng, Jamie Smith, Michael Rubinstein, Huiwen Chang, Katherine L. Bouman, William T. Freeman
ICCV, 2023
Webpage Paper Code
Visual Vibration Tomography: Estimating Interior Material Properties from Monocular Video
Berthy T. Feng, Alexander C. Ogren, Chiara Daraio, Katherine L. Bouman
CVPR, 2022
Oral, Best Paper Finalist (top 1.6% of accepted papers)
Webpage Paper Code
Other Publications
U-DAVI: Uncertainty-aware Diffusion-prior-based Amortized Variational Inference for Image Reconstruction
Ayush Varney, Katherine L. Bouman, Berthy T. Feng
ICASSP, 2026
InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems
Hongkai Zheng, Wenda Chu, Bingliang Zhang, Zihui Wu, Austin Wang, Berthy T. Feng, Caifeng Zou, Yu Sun, Nikola Borislavov Kovachki, Zachary E. Ross, Katherine L. Bouman, Yisong Yue
ICLR, 2025
Spotlight (top 5.1% of submitted papers)
Paper
Provable Probabilistic Imaging Using Score-Based Generative Priors
Yu Sun, Zihui Wu, Yifan Chen, Berthy T. Feng, Katherine L. Bouman
IEEE Transactions on Computational Imaging (TCI), 2024
Paper
Score-based Diffusion Models for Photoacoustic Tomography Image Reconstruction
Sreemanti Dey, Snigdha Saha, Berthy T. Feng, Manxiu Cui, Laure Delisle, Oscar Leong, Lihong V. Wang, Katherine L. Bouman
ICASSP, 2024
Paper
Gaussian process regression as a surrogate model for the computation of dispersion relations
Alexander C. Ogren, Berthy T. Feng, Katherine L. Bouman, Chiara Daraio
Computer Methods in Applied Mechanics and Engineering (CMAME), 2024
Paper
Towards Unique and Informative Captioning of Images
Zeyu Wang, Berthy T. Feng, Karthik Narasimhan, Olga Russakovsky
ECCV, 2020
Paper Code
Learning Bandwidth Expansion Using Perceptually-Motivated Loss
Berthy T. Feng, Zeyu Jin, Jiaqi Su, Adam Finkelstein
ICASSP, 2019
Paper Code
