ADIR: Adaptive Diffusion for Image Reconstruction


Shady Abu-Hussein (Tel Aviv University), Tom Tirer (Tel Aviv University), Raja Giryes (Bar Ilan University)
The 35th British Machine Vision Conference

Abstract

Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a clean image from a degraded observation. In this work, we introduce a conditional sampling framework that leverages the powerful priors learned by diffusion models while enforcing consistency with the available measurements. To further adapt pre-trained diffusion models to the specific degradation at hand, we propose a novel fine-tuning strategy. In particular, we employ LoRA-based adaptation using images that are semantically and visually similar to the degraded input, efficiently retrieved from a large and diverse dataset via an off-the-shelf vision–language model. We evaluate our approach on two leading publicly available diffusion models—Stable Diffusion and Guided Diffusion—and demonstrate that our method, termed $\textbf{A}$daptive $\textbf{D}$iffusion for $\textbf{I}$mage $\textbf{R}$econstruction ($\textbf{ADIR}$), yields substantial improvements across a range of image reconstruction tasks. Code is available at https://github.com/shadyabh/ADIR.

Citation

@inproceedings{Abu-Hussein_2025_BMVC,
author    = {Shady Abu-Hussein and Tom Tirer and Raja Giryes},
title     = {ADIR: Adaptive Diffusion for Image Reconstruction},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_261/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection