Reconstruction-Aware Distribution Matching for Inverse Problems with Unpaired Data
Abstract
Recovering the forward operator of an imaging system from unpaired data avoids both calibration hardware and the clean/degraded pairs that supervision requires-pairs that, for a real lens, are often impossible to acquire. Existing unpaired approaches that explicitly estimate the forward operator by distribution matching evaluate a candidate only through the measurements it generates, whose distribution should match that of the real ones. Components suppressed by the operator are barely present in the degraded images, and therefore barely constrain the operator under such a criterion. Yet inversion precisely tries to recover them. As a result, two operators that are nearly indistinguishable as forward models can invert very differently. We address this by adding a comparison on the clean side: real degraded images, once restored, should be distributed like clean ones. Restorations are computed by a differentiable plug-and-play algorithm parameterized by the operator being learned. On spatially varying PSF calibration and blind super-resolution, the method recovers more accurate operators than degraded-side matching alone, and closes much of the gap to restoration with the true operator.
Related
- Flow Matching for Fast Posterior Sampling in Bayesian Inverse Problems
- Physics-Guided Conditional Flow Matching with Energy Regularization for Robust PDE Inverse Problems
- Finite inverse nodal problems for singular weighted Sturm--Liouville equations: variational selection and spectral matching
- Reconstruction methods for inverse scattering problems with phaseless data
- DisKO: Deep Koopman Learning in Distribution Space from Unpaired Snapshots
BibTeX
@misc{ryckeboer2026reconstructionaware,
title = {{Reconstruction-Aware Distribution Matching for Inverse Problems with Unpaired Data}},
author = {Thomas Ryckeboer and Giacomo Meanti and Julien Mairal},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.06297},
eprint = {2610.06297},
archivePrefix = {arXiv},
url = {https://inria.hal.science/hal-05774305v1},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - Reconstruction-Aware Distribution Matching for Inverse Problems with Unpaired Data
AU - Thomas Ryckeboer
AU - Giacomo Meanti
AU - Julien Mairal
PY - 2026
DA - 2026/10/01
PB - HAL
DO - 10.48550/arxiv.2610.06297
UR - https://inria.hal.science/hal-05774305v1
AB - Recovering the forward operator of an imaging system from unpaired data avoids both calibration hardware and the clean/degraded pairs that supervision requires-pairs that, for a real lens, are often impossible to acquire. Existing unpaired approaches that explicitly estimate the forward operator by distribution matching evaluate a candidate only through the measurements it generates, whose distribution should match that of the real ones. Components suppressed by the operator are barely present in the degraded images, and therefore barely constrain the operator under such a criterion. Yet inversion precisely tries to recover them. As a result, two operators that are nearly indistinguishable as forward models can invert very differently. We address this by adding a comparison on the clean side: real degraded images, once restored, should be distributed like clean ones. Restorations are computed by a differentiable plug-and-play algorithm parameterized by the operator being learned. On spatially varying PSF calibration and blind super-resolution, the method recovers more accurate operators than degraded-side matching alone, and closes much of the gap to restoration with the true operator.
ER -