Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers
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.
Code (1)
Tasks
Image RestorationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Universal Image Restoration via Internalized Chain-of-Thought Reasoning
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 EditingQ-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model
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+2RIRF: Reasoning Image Restoration Framework
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 RestorationDeep Equilibrium Diffusion Restoration with Parallel Sampling
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 RestorationProxies for Distortion and Consistency with Applications for Real-World Image Restoration
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