Deep LoRA-Unfolding Networks for Image Restoration
IEEE Transactions on Image Processing · 2026 · 35 · 1858-1869
DOI: 10.1109/tip.2026.3661406 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Xiangming Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Major Project of Basic and Applied Basic Research.
Abstract (Originalsprache)
Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging reconstruction, compressive sensing and super-resolution. It unfolds the iterative optimization steps into a stack of sequentially linked blocks. Each block consists of a Gradient Descent Module (GDM) and a Proximal Mapping Module (PMM) which is equivalent to a denoiser from a Bayesian perspective, operating on Gaussian noise with a known level. However, existing DUNs suffer from two critical limitations: 1) their PMMs share identical architectures and denoising objectives across stages, ignoring the need for stage-specific adaptation to varying noise levels; and 2) their chain of structurally repetitive blocks results in severe parameter redundancy and high memory consumption, hindering deployment in large-scale or resource-constrained scenarios. To address these challenges, we introduce generalized Deep Low-rank Adaptation (LoRA) Unfolding Networks for image restoration, named LoRun, harmonizing denoising objectives and adapting different denoising levels between stages with compressed memory usage for more efficient DUN. LoRun introduces a novel paradigm where a single pretrained base denoiser is shared across all stages, while lightweight, stage-specific LoRA adapters are injected into the PMMs to dynamically modulate denoising behavior according to the noise level at each unfolding step. This design decouples the core restoration capability from task-specific adaptation, enabling precise control over denoising intensity without duplicating full network parameters and achieving up to $N$ times parameter reduction for an $N$ -stage DUN with on-par or better performance. Extensive experiments conducted on three IR tasks validate the efficiency of our method.
Förderung
- National Natural Science Foundation of China
- Guangdong Major Project of Basic and Applied Basic Research
Zitieren
APA
Wang, X., Zeng, H., Sun, B., Cao, J., Zhang, K., Shen, Q., & Chen, Y. (2026). Deep LoRA-Unfolding Networks for Image Restoration. IEEE Transactions on Image Processing, 35, 1858-1869. https://doi.org/10.1109/tip.2026.3661406
Vancouver
Wang X, Zeng H, Sun B, Cao J, Zhang K, Shen Q, et al. Deep LoRA-Unfolding Networks for Image Restoration. IEEE Transactions on Image Processing. 2026;35:1858-1869. doi:10.1109/tip.2026.3661406
BibTeX
@article{Wang2026,
author = {Wang, Xiangming and Zeng, Haijin and Sun, Benteng and Cao, Jiezhang and Zhang, Kai and Shen, Qiangqiang and Chen, Yongyong},
title = {Deep LoRA-Unfolding Networks for Image Restoration},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {1858--1869},
doi = {10.1109/tip.2026.3661406}
}
EUVIMED