paper-with-me

홈 › Papers

Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers

2024-10-11 · Jin Cao, Deyu Meng, Xiangyong Cao

Despite previous image restoration (IR) methods have often concentrated on isolated degradations, recent research has increasingly focused on addressing composite degradations involving a complex combination of multiple isolated degradations. However, current IR methods for composite degradations require building training data that contain an exponential number of possible degradation combinations, which brings in a significant burden. To alleviate this issue, this paper proposes a new task setting, i.e. Universal Image Restoration (UIR). Specifically, UIR doesn't require training on all the degradation combinations but only on a set of degradation bases and then removing any degradation that these bases can potentially compose in a zero-shot manner. Inspired by the Chain-of-Thought that prompts large language models (LLMs) to address problems step-by-step, we propose Chain-of-Restoration (CoR) mechanism, which instructs models to remove unknown composite degradations step-by-step. By integrating a simple Degradation Discriminator into pre-trained multi-task models, CoR facilitates the process where models remove one degradation basis per step, continuing this process until the image is fully restored from the unknown composite degradation. Extensive experiments show that CoR can significantly improve model performance in removing composite degradations, achieving comparable or better results than those state-of-the-art (SoTA) methods trained on all degradations.

📄 PDF Abstract BibTeX arXiv:2410.08688

Code (1)

toummhus/chain-of-restoration 공식 구현

Tasks

Image Restoration

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Universal Image Restoration via Internalized Chain-of-Thought Reasoning

2026-06-16 · Yu Guo, Zhengru Fang, Shengfeng He, Senkang Hu 외 arxiv

Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are common, their performance declines as degrad…

Image RestorationImage Editing

Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model

2025-04-09 · Yingjie Zhou, JieZhang Cao, ZiCheng Zhang, Farong Wen 외

Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Training specific models for specific degradat…

Image Quality AssessmentImage RestorationLanguage ModelingLanguage Modelling+2

RIRF: Reasoning Image Restoration Framework

2026-04-10 · Wending Yan, Rongkai Zhang, Kaihua Tang, Yu Cheng 외 arxiv

Universal image restoration (UIR) aims to recover clean images from diverse and unknown degradations using a unified model. Existing UIR methods primarily focus on pixel reconstruction and often lack explicit diagnostic …

Reinforcement LearningImage Restoration

Deep Equilibrium Diffusion Restoration with Parallel Sampling

2023-11-20 · CVPR 2024 1 · JieZhang Cao, Yue Shi, Kai Zhang, Yulun Zhang 외

Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Due to the inherent property of diffusion models, most …

Image Restoration

Proxies for Distortion and Consistency with Applications for Real-World Image Restoration

2025-01-21 · Sean Man, Guy Ohayon, Ron Raphaeli, Michael Elad

Real-world image restoration deals with the recovery of images suffering from an unknown degradation. This task is typically addressed while being given only degraded images, without their corresponding ground-truth vers…

Image Restoration