Papers › Image Reconstruction via Deep Image Prior Subspaces

Image Reconstruction via Deep Image Prior Subspaces

20 Feb 2023arXiv:2302.10279archive 2025-07-28

Riccardo Barbano, Javier Antorán, Johannes Leuschner, José Miguel Hernández-Lobato, Bangti Jin, Željko Kereta

Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill this gap, but bring a host of new issues: the susceptibility to overfitting due to a lack of robust early stopping strategies and unstable convergence. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters, employing a synergy of dimensionality reduction techniques and second order optimisation methods. The low-dimensionality of the subspace reduces DIP's tendency to fit noise and allows the use of stable second order optimisation methods, e.g., natural gradient descent or L-BFGS. Experiments across both image restoration and tomographic tasks of different geometry and ill-posedness show that second order optimisation within a low-dimensional subspace is favourable in terms of optimisation stability to reconstruction fidelity trade-off.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

anonsubdip/subspace_dip officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dimensionality ReductionImage ReconstructionImage Restoration

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Early StoppingNatural Gradient Descent

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections