Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Link opens in a new tab
Search content at Illinois Experts
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
AmbientFlow: Invertible generative models from incomplete, noisy measurements
Varun A. Kelkar
, Rucha M. Deshpande
,
Arindam Banerjee
,
Mark A. Anastasio
Siebel School of Computing and Data Science
Electrical and Computer Engineering
National Center for Supercomputing Applications (NCSA)
Bioengineering
Coordinated Science Lab
Biomedical and Translational Sciences
Clinical Sciences
Beckman Institute for Advanced Science and Technology
Research output
:
Contribution to journal
›
Article
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'AmbientFlow: Invertible generative models from incomplete, noisy measurements'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Invertible
100%
Noisy Measurements
100%
Generative Models
100%
Flow-based Generative Model
100%
Image Reconstruction
66%
Incomplete Data
66%
Data Sharing
33%
Acquisition Time
33%
Diverse Sample
33%
Noisy Data
33%
Computational Imaging
33%
Density Estimates
33%
Object Distributions
33%
Noisy-OR
33%
High-dose Radiation
33%
Posterior Sampling
33%
Inference Tasks
33%
Partially Observed
33%
Imaging Sciences
33%
Variational Bayesian Inference
33%
High-quality Dataset
33%
Learning Flow
33%
Computer Science
Generative Model
100%
Image Reconstruction
40%
Data Sharing
20%
Acquisition Time
20%
Potential Application
20%
Density Estimate
20%
Inference Task
20%
Engineering
Generative Model
100%
Image Reconstruction
40%
Potential Application
20%
Acquisition Time
20%
Numerical Study
20%
Density Estimate
20%