activity
20202026
most citedScore-Based Diffusion Models for Photoacoustic Tomography Image Reconstruction

10 citations · 13 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

Visual Surface Wave Elastography: Revealing Subsurface Physical Properties via Visible Surface Waves

Alexander C. Ogren, Berthy T. Feng, Jihoon Ahn +2

Wave propagation on the surface of a material contains information about physical properties beneath its surface. We propose a method for inferring the thickness and stiffness of a…

cs.CV2025

Teaching Humans Subtle Differences with DIFFusion

Mia Chiquier, Orr Avrech, Yossi Gandelsman +3

Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generati…

cs.CV2025

STeP: A Framework for Solving Scientific Video Inverse Problems with Spatiotemporal Diffusion Priors

Bingliang Zhang, Zihui Wu, Berthy T. Feng +3

Reconstructing spatially and temporally coherent videos from time-varying measurements is a fundamental challenge in many scientific domains. A major difficulty arises from the spa…

cs.CV2023

Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior

Berthy T. Feng, Katherine L. Bouman

We propose a surrogate function for efficient yet principled use of score-based priors in Bayesian imaging. We consider ill-posed inverse imaging problems in which one aims for a c…

cs.CV2023

Score-Based Diffusion Models as Principled Priors for Inverse Imaging

Berthy T. Feng, Jamie Smith, Michael Rubinstein +3

Priors are essential for reconstructing images from noisy and/or incomplete measurements. The choice of the prior determines both the quality and uncertainty of recovered images. W…

cs.CV20203 cited

Towards Unique and Informative Captioning of Images

Zeyu Wang, Berthy Feng, Karthik Narasimhan +1

Despite considerable progress, state of the art image captioning models produce generic captions, leaving out important image details. Furthermore, these systems may even misrepres…