UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptation

• URL: http://arxiv.org/abs/2409.20197v1
• Date: Mon, 30 Sep 2024 11:16:56 GMT
• Title: UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptation
• Authors: Cheng Zhang, Dong Gong, Jiumei He, Yu Zhu, Jinqiu Sun, Yanning Zhang,
• Abstract summary: Existing unified methods treat multi-degradation image restoration as a multi-task learning problem. We propose a universal image restoration framework based on multiple low-rank adapters (LoRA) from multi-domain transfer learning. Our framework leverages the pre-trained generative model as the shared component for multi-degradation restoration and transfers it to specific degradation image restoration tasks.
• Score: 50.27688690379488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing unified methods typically treat multi-degradation image restoration as a multi-task learning problem. Despite performing effectively compared to single degradation restoration methods, they overlook the utilization of commonalities and specificities within multi-task restoration, thereby impeding the model's performance. Inspired by the success of deep generative models and fine-tuning techniques, we proposed a universal image restoration framework based on multiple low-rank adapters (LoRA) from multi-domain transfer learning. Our framework leverages the pre-trained generative model as the shared component for multi-degradation restoration and transfers it to specific degradation image restoration tasks using low-rank adaptation. Additionally, we introduce a LoRA composing strategy based on the degradation similarity, which adaptively combines trained LoRAs and enables our model to be applicable for mixed degradation restoration. Extensive experiments on multiple and mixed degradations demonstrate that the proposed universal image restoration method not only achieves higher fidelity and perceptual image quality but also has better generalization ability than other unified image restoration models. Our code is available at https://github.com/Justones/UIR-LoRA.

Related papers

• LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration [62.3751291442432]
  We propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. LoRA-IR achieves state-of-the-art performance across 14 image restoration tasks and 29 benchmarks.
  arXiv  Detail & Related papers  (2024-10-20T13:00:24Z)
• Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers [53.298698981438]
  We propose Universal Image Restoration (UIR), a new task setting that requires models to be trained on a set of degradation bases and then remove any degradation that these bases can potentially compose in a zero-shot manner. Inspired by the Chain-of-Thought which prompts LLMs to address problems step-by-step, we propose the Chain-of-Restoration (CoR) CoR instructs models to step-by-step remove unknown composite degradations.
  arXiv  Detail & Related papers  (2024-10-11T10:21:42Z)
• Multi-Scale Representation Learning for Image Restoration with State-Space Model [13.622411683295686]
  We propose a novel Multi-Scale State-Space Model-based (MS-Mamba) for efficient image restoration. Our proposed method achieves new state-of-the-art performance while maintaining low computational complexity.
  arXiv  Detail & Related papers  (2024-08-19T16:42:58Z)
• Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition [44.80645807358389]
  HLNet is a Bracketing Image Restoration and Enhancement method based on high-low frequency decomposition. We employ two modules for feature extraction: shared weight modules and non-shared weight modules. In the non-shared weight modules, we introduce the High-Low Frequency Decomposition Block (HLFDB), which employs different methods to handle high-low frequency information.
  arXiv  Detail & Related papers  (2024-04-21T05:11:37Z)
• Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models [14.25759541950917]
  This work leverages a capable vision-language model and a synthetic degradation pipeline to learn image restoration in the wild (wild IR) Our base diffusion model is the image restoration SDE (IR-SDE)
  arXiv  Detail & Related papers  (2024-04-15T12:34:21Z)
• InstructIR: High-Quality Image Restoration Following Human Instructions [61.1546287323136]
  We present the first approach that uses human-written instructions to guide the image restoration model. Our method, InstructIR, achieves state-of-the-art results on several restoration tasks.
  arXiv  Detail & Related papers  (2024-01-29T18:53:33Z)
• Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild [57.06779516541574]
  SUPIR (Scaling-UP Image Restoration) is a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. We collect a dataset comprising 20 million high-resolution, high-quality images for model training, each enriched with descriptive text annotations.
  arXiv  Detail & Related papers  (2024-01-24T17:58:07Z)
• 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)
• All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation [47.00239809958627]
  We propose a novel All-in-one Multi-degradation Image Restoration Network (AMIRNet) AMIRNet learns a degradation representation for unknown degraded images by progressively constructing a tree structure through clustering. This tree-structured representation explicitly reflects the consistency and discrepancy of various distortions, providing a specific clue for image restoration.
  arXiv  Detail & Related papers  (2023-08-06T04:51:41Z)

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.