REVIEW 11 cited by
DeepInverse: A Python package for solving imaging inverse problems with deep learning
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
DeepInverse is an open-source PyTorch-based library for solving imaging inverse problems. The library covers all crucial steps in image reconstruction from the efficient implementation of forward operators (e.g., optics, MRI, tomography), to the definition and resolution of variational problems and the design and training of advanced neural network architectures. In this paper, we describe the main functionality of the library and discuss the main design choices.
Forward citations
Cited by 11 Pith papers
-
Geometry-Aware Discretization Error of Diffusion Models
First-order asymptotic expansions of weak and Fréchet discretization errors in diffusion sampling are derived, explicit under Gaussian data through covariance geometry and robust to other data geometries.
-
P-Flow: Proxy-gradient Flows for Linear Inverse Problems
P-Flow stabilizes flow-matching models for inverse problems via proxy gradients and Gaussian spherical projections, avoiding long-chain differentiation while maintaining prior consistency.
-
Preconditioned Regularized Wasserstein Proximal Sampling
A preconditioned regularized Wasserstein proximal sampling algorithm is introduced for particle-based approximation of Gibbs distributions, featuring a PDE-derived kernel formulation and non-asymptotic convergence ana...
-
A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP
MAP blind deconvolution fails with diffusion priors because blurry images are more likely, while true solutions persist only as local minima reachable with good initialization.
-
Deep Scene-Driven Ordering of Hadamard Basis for Single-Pixel Spectral Imaging
A scene-driven neural network orders Hadamard sensing patterns for single-pixel spectral imaging, improving VIS/NIR reconstructions over fixed orderings at low sampling ratios.
-
PnP-IPA: A Provably Convergent Plug-and-Play Inexact Proximal Algorithm for Nonconvex Imaging Problems
An inexact proximal PnP algorithm with adaptive line search converges globally for nonconvex imaging objectives without any bound on the regularization parameter.
-
P-Flow: Proxy-gradient Flows for Linear Inverse Problems
P-Flow solves linear inverse problems by optimizing the flow's source latent with a proxy gradient and a Gaussian-sphere projection, matching or beating prior restoration methods at far lower cost.
-
UTOPY: Unrolling Algorithm Learning via Fidelity Homotopy for Inverse Problems
UTOPY trains unrolling algorithms for ill-posed inverse problems via a fidelity homotopy path from synthetic well-posed to real ill-posed sensing operators, yielding up to 2.5 dB PSNR gains.
-
P-Flow: Proxy-gradient Flows for Linear Inverse Problems
P-Flow replaces direct differentiation through long flow paths with a proxy gradient update plus Gaussian spherical projection to stabilize reconstruction in linear inverse problems.
-
Stabilizing RED using the Koopman Operator
A Koopman-operator-based monitor shrinks the RED step size whenever a low-dimensional model of the iterates predicts divergence, preventing PSNR collapse.
-
Learned iterative networks: An operator learning perspective
Learned iterative reconstruction networks can be uniformly described as operator learning: the unrolled architecture fixes how to compute while the loss and data fix what to compute; for nonlinear inverse problems the...
Discussion (0). Sign in to comment.