发表机构
Xiaomi Corporation（小米公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对全场景图像恢复现有方法采用统一策略忽略区域退化差异的问题，提出MGN-AIR框架，通过像素级多模态引导实现更精细恢复，在多任务基准上性能显著优于现有方法。
AI 中文摘要
全场景图像恢复是一项统一的低级视觉任务，旨在用单个模型从遭受各类及不同程度退化的输入中有效恢复高质量图像。近期研究通过学习适配退化的提示词或网络架构取得了显著进展，但这些方法通常对整幅图像采用统一恢复策略，忽略了不同区域可能遭受不同类型退化及程度各异的严重程度。相比之下，我们提出在像素层面执行恢复，从而实现对恢复过程更精细、精准的控制。具体而言，我们提出MGN-AIR，一种用于全场景图像恢复的新型像素级恢复框架。我们的方法首先学习估计像素级视觉提示词，随后利用文本和视觉提示词提供全局与局部退化线索，引导模型在每个像素处关注何处及如何恢复。我们在多个全场景图像恢复基准上开展了广泛实验，涵盖去噪、去雨、去模糊、去雾、去雪及低光增强等多种任务。实验结果表明，我们提出的方法始终显著优于现有方法。
英文摘要
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.
CommentsAccepted by ACMMM2026 as Oral Paper
