# Locally-Supervised Global Image Restoration

Source: [Locally-Supervised Global Image Restoration](<https://www.sota2.com/research/paper/690ad9e45fbd54038400456e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-24T05:00:03.763Z

Authors: Benjamin Walder, Daniel Toader, Robert Nuster, G\\"unther Paltauf, Peter Burgholzer, Gregor Langer, Lukas Krainer, Markus Haltmeier

Published: 2025-11-03T19:12:25.000Z

## Abstract

We address the problem of image reconstruction from incomplete measurements, encompassing both upsampling and inpainting, within a learning-based framework. Conventional supervised approaches require fully sampled ground truth data, while self-supervised methods allow incomplete ground truth but typically rely on random sampling that, in expectation, covers the entire image. In contrast, we consider fixed, deterministic sampling patterns with inherently incomplete coverage, even in expectation. To overcome this limitation, we exploit multiple invariances of the underlying image distribution, which theoretically allows us to achieve the same reconstruction performance as fully supervised approaches. We validate our method on optical-resolution image upsampling in photoacoustic microscopy (PAM), demonstrating competitive or superior results while requiring substantially less ground truth data.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Reconstruction on OR-PAM human lung tissue sections 5 different images (test)](<https://www.sota2.com/research/sota/image-reconstruction-on-or-pam-human-lung-tissue-sections-5-different-images-test.md>): Image Reconstruction; OR-PAM human lung tissue sections 5 different images (test); MSE: 2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.01998>)

[PDF](<https://arxiv.org/pdf/2511.01998.pdf>)
