REVIEW 4 cited by
Deep Bayesian Inversion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Characterizing statistical properties of solutions of inverse problems is essential for decision making. Bayesian inversion offers a tractable framework for this purpose, but current approaches are computationally unfeasible for most realistic imaging applications in the clinic. We introduce two novel deep learning based methods for solving large-scale inverse problems using Bayesian inversion: a sampling based method using a WGAN with a novel mini-discriminator and a direct approach that trains a neural network using a novel loss function. The performance of both methods is demonstrated on image reconstruction in ultra low dose 3D helical CT. We compute the posterior mean and standard deviation of the 3D images followed by a hypothesis test to assess whether a "dark spot" in the liver of a cancer stricken patient is present. Both methods are computationally efficient and our evaluation shows very promising performance that clearly supports the claim that Bayesian inversion is usable for 3D imaging in time critical applications.
Forward citations
Cited by 4 Pith papers
-
Prior laundering: learned priors with inherited, undetectable overconfidence
Training a learned prior on legacy reconstructions equals one EM step of the old regularizer, freezing its belief on the operator's blind subspace and yielding overconfident, measurement-undetectable uncertainty.
-
Posterior Variance Is a Constraint Map, Not an Error Map: Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT
In radiative Gaussian splatting for sparse-view CT, posterior variance is a data-constraint map: it ranks error over the whole volume (14/15 scenes) but collapses inside foreground tissue (median Spearman 0.11, 0/15 s...
-
An invertible generative model for forward and inverse problems
A single invertible map constructed from two triangular normalizing flows can conditionally sample both the likelihood and the posterior in Bayesian inverse problems.
-
Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height
A conditional GAN trained on WRF-SFIRE simulations reconstructs fire arrival times from VIIRS and GOES data, matching aircraft-measured perimeters with an average Sørensen-Dice coefficient of 0.81 on five real fires.
Discussion (0). Sign in to comment.