Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models

• URL: http://arxiv.org/abs/2601.03391v1
• Date: Tue, 06 Jan 2026 19:56:16 GMT
• Title: Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models
• Authors: M. Akın Yılmaz, Ahmet Bilican, Burak Can Biner, A. Murat Tekalp,
• Abstract summary: We show that powerful pre-trained text-conditioned image editing models can be efficiently adapted for multiple restoration tasks.<n>Our approach fine-tunes LoRA adapters on FLUX.1 Kontext, a state-of-the-art 12B parameter flow matching model for image-to-image translation.
• Score: 4.573600918393017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. We challenge this paradigm by demonstrating that powerful pre-trained text-conditioned image editing models can be efficiently adapted for multiple restoration tasks through parameter-efficient fine-tuning with remarkably few examples. Our approach fine-tunes LoRA adapters on FLUX.1 Kontext, a state-of-the-art 12B parameter flow matching model for image-to-image translation, using only 16-128 paired images per task, guided by simple text prompts that specify the restoration operation. Unlike existing methods that train specialized restoration networks from scratch with thousands of samples, we leverage the rich visual priors already encoded in large-scale pre-trained editing models, dramatically reducing data requirements while maintaining high perceptual quality. A single unified LoRA adapter, conditioned on task-specific text prompts, effectively handles multiple degradations including denoising, deraining, and dehazing. Through comprehensive ablation studies, we analyze: (i) the impact of training set size on restoration quality, (ii) trade-offs between task-specific versus unified multi-task adapters, (iii) the role of text encoder fine-tuning, and (iv) zero-shot baseline performance. While our method prioritizes perceptual quality over pixel-perfect reconstruction metrics like PSNR/SSIM, our results demonstrate that pre-trained image editing models, when properly adapted, offer a compelling and data-efficient alternative to traditional image restoration approaches, opening new avenues for few-shot, prompt-guided image enhancement. The code to reproduce our results are available at: https://github.com/makinyilmaz/Edit2Restore

Related papers

• EditInfinity: Image Editing with Binary-Quantized Generative Models [64.05135380710749]
  We investigate the parameter-efficient adaptation of binary-quantized generative models for image editing.<n>Specifically, we propose EditInfinity, which adapts emphInfinity, a binary-quantized generative model, for image editing.<n>We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation.
  arXiv  Detail & Related papers  (2025-10-23T05:06:24Z)
• Learning an Image Editing Model without Image Editing Pairs [83.03646586929638]
  Recent image editing models have achieved impressive results while following natural language editing instructions.<n>They rely on supervised fine-tuning with large datasets of input-target pairs.<n>Current workarounds use synthetic training pairs that leverage the zero-shot capabilities of existing models.<n>We present a new training paradigm that eliminates the need for paired data entirely.
  arXiv  Detail & Related papers  (2025-10-16T17:59:57Z)
• Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration [1.9336815376402718]
  We propose a strategy for compressing multi-task image restoration models.<n>The proposed model, namely MIR-L, utilizes an iterative pruning strategy that removes low-magnitude weights.<n>Tests show that MIR-L retains only 10% of the trainable parameters while maintaining high image restoration performance.
  arXiv  Detail & Related papers  (2025-10-16T09:04:05Z)
• Policy Optimized Text-to-Image Pipeline Design [73.9633527029941]
  We introduce a novel reinforcement learning-based framework for text-to-image generation.<n>Our approach first trains an ensemble of reward models capable of predicting image quality scores directly from prompt-workflow combinations.<n>We then implement a two-phase training strategy: initial vocabulary training followed by GRPO-based optimization.
  arXiv  Detail & Related papers  (2025-05-27T17:50:47Z)
• Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration [25.65952375846516]
  We find that the well-trained large T2I model (i.e., Flux) is able to produce a variety of high-quality images aligned with real-world distributions.<n>A novel light-weighted adapter (FluxIR) with squeeze-and-excitation layers is also carefully designed to control the large Diffusion Transformer (DiT)-based T2I model.
  arXiv  Detail & Related papers  (2025-04-21T15:05:22Z)
• HAIR: Hypernetworks-based All-in-One Image Restoration [46.681872835394095]
  Hair is a Hypernetworks-based All-in-One Image Restoration plug-and-play method. It generates parameters based on the input image and thus makes the model to adapt to specific degradation dynamically. It can significantly improve the performance of existing image restoration models in a plug-and-play manner, both in single-task and All-in-One settings.
  arXiv  Detail & Related papers  (2024-08-15T11:34:33Z)
• Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method [7.487270862599671]
  We propose a new training paradigm for general image restoration models, which we name bfReview Learning. This approach begins with sequential training of an image restoration model on several degraded datasets, combined with a review mechanism. We design a lightweight all-purpose image restoration network that can efficiently reason about degraded images with 4K resolution on a single consumer-grade GPU.
  arXiv  Detail & Related papers  (2024-08-13T08:08:45Z)
• Efficient and Versatile Robust Fine-Tuning of Zero-shot Models [34.27380518351181]
  We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Our experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
  arXiv  Detail & Related papers  (2024-08-11T11:37:43Z)
• PromptFix: You Prompt and We Fix the Photo [84.69812824355269]
  Diffusion models equipped with language models demonstrate excellent controllability in image generation tasks. The lack of diverse instruction-following data hampers the development of models. We propose PromptFix, a framework that enables diffusion models to follow human instructions.
  arXiv  Detail & Related papers  (2024-05-27T03:13:28Z)
• Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration [50.81374327480445]
  We introduce a novel concept positing that intricate image degradation can be represented in terms of elementary degradation. We propose the Unified-Width Adaptive Dynamic Network (U-WADN), consisting of two pivotal components: a Width Adaptive Backbone (WAB) and a Width Selector (WS) The proposed U-WADN achieves better performance while simultaneously reducing up to 32.3% of FLOPs and providing approximately 15.7% real-time acceleration.
  arXiv  Detail & Related papers  (2024-01-24T04:25:12Z)
• Exposure Bracketing Is All You Need For A High-Quality Image [50.822601495422916]
  Multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution.<n>We propose to utilize exposure bracketing photography to get a high-quality image by combining these tasks in this work.<n>In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed.
  arXiv  Detail & Related papers  (2024-01-01T14:14:35Z)
• Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts [52.39959535724677]
  We introduce an alternative solution to improve the generalization of image restoration models. We propose AdaptIR, a Mixture-of-Experts (MoE) with multi-branch design to capture local, global, and channel representation bases. Our AdaptIR achieves stable performance on single-degradation tasks, and excels in hybrid-degradation tasks, with fine-tuning only 0.6% parameters for 8 hours.
  arXiv  Detail & Related papers  (2023-12-12T14:27:59Z)
• Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction [62.955327005837475]
  Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
  arXiv  Detail & Related papers  (2023-10-29T13:58:57Z)
• Controlling Vision-Language Models for Multi-Task Image Restoration [6.239038964461397]
  We present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks. Our approach advances state-of-the-art performance on both emphdegradation-specific and emphunified image restoration tasks.
  arXiv  Detail & Related papers  (2023-10-02T09:10:16Z)
• Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration [79.04007257606862]
  This paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks.
  arXiv  Detail & Related papers  (2023-09-12T07:50:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.