Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors propose a new way to fix pictures that have different kinds of damage, like noise or blur, all at once using one model. Unlike previous methods that treat the whole image the same, their method works at the pixel level, customizing the fix for each tiny part of the image. They use special cues, both visual and text-based, to guide exactly how to restore each pixel. Tests show their approach works better than current methods across many image restoration tasks.
image restorationpixel-level restorationvisual prompttextual promptdenoisingdeblurringderainingdehazinglow-level vision
Authors
Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng
Abstract
All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model. Recent works have achieved remarkable progress by learning degradation-adaptive prompts or network architectures. However, these methods typically apply a uniform restoration strategy across the entire image, neglecting the fact that different regions may suffer from distinct degradation types and varying degrees of severity. In contrast, we propose to perform restoration at the pixel level, thereby enabling more fine-grained and precise control over the restoration process. Specifically, we present MGN-AIR, a novel pixel-level restoration framework for all-in-one image restoration. Our approach first learns to estimate a pixel-level visual prompt. Then, it leverages both textual and visual prompts to provide global and local degradation cues, guiding the model on where to look and how to restore at each pixel. We conduct extensive experiments on multiple all-in-one image restoration benchmarks, covering a wide range of tasks including denoising, deraining, deblurring, dehazing, desnowing, and low-light enhancement. Experimental results demonstrate that our proposed method consistently and significantly outperforms existing approaches.