REVIEW 6 cited by
Learned convex regularizers for inverse problems
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
Signed reviews
read the original abstract
We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional. The ICNN-based convex regularizer is trained adversarially to discern ground-truth images from unregularized reconstructions. Convexity of the regularizer is desirable since (i) one can establish analytical convergence guarantees for the corresponding variational reconstruction problem and (ii) devise efficient and provable algorithms for reconstruction. In particular, we show that the optimal solution to the variational problem converges to the ground-truth if the penalty parameter decays sub-linearly with respect to the norm of the noise. Further, we prove the existence of a sub-gradient-based algorithm that leads to a monotonically decreasing error in the parameter space with iterations. To demonstrate the performance of our approach for solving inverse problems, we consider the tasks of deblurring natural images and reconstructing images in computed tomography (CT), and show that the proposed convex regularizer is at least competitive with and sometimes superior to state-of-the-art data-driven techniques for inverse problems.
Forward citations
Cited by 6 Pith papers
-
Nonlinear Joint Spectral Radius
For switched nonlinear systems whose maps are sub-homogeneous and order-preserving on a cone, a nonlinear joint spectral radius is shown to characterize asymptotic stability and bound the worst-case separation growth ...
-
MAP Image Recovery with Guarantees using Locally Convex Multi-Scale Energy (LC-MUSE) Model
A locally convex multi-scale energy prior with local monotonicity constraints gives provable reconstruction guarantees and MRI results that match non-convex deep baselines.
-
Benchmarking learned algorithms for computed tomography image reconstruction tasks
A reproducible benchmark of learned CT reconstruction methods on real experimental data, covering post-processing, unrolled, learned regularizer, and plug-and-play methods across five tasks.
-
Augmented NETT Regularization of Inverse Problems
Adding a manifold-distance penalty to NETT yields a coercive learned regularizer with convergence guarantees and competitive CT reconstructions.
-
Good Things Come in Pairs: Paired Autoencoders for Inverse Problems
Paired autoencoders give likelihood-free inverse-problem solvers with out-of-distribution metrics, and their new variational variants add uncertainty sampling.
-
An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation
A computable a-posteriori bound on the inexact piggyback hypergradient enables adaptive tolerance and step-size control for bilevel learning of convex regularizers.
Discussion (0). Continue with ORCID to comment.