RealRestorer：基于大规模图像编辑模型的通用真实世界图像修复研究

摘要

真实世界退化条件下的图像修复对于自动驾驶、目标检测等下游任务至关重要。然而现有修复模型常受限于训练数据的规模与分布，导致在真实场景中的泛化能力不足。近期大规模图像编辑模型在修复任务中展现出强大的泛化能力，特别是如Nano Banana Pro等闭源模型能够保持图像一致性的同时完成修复。但实现此类大型通用模型的优异性能需要海量数据与巨大算力成本。为解决该问题，我们构建了涵盖九种常见真实退化类型的大规模数据集，并训练出顶尖开源模型以缩小与闭源方案的差距。此外，我们推出包含464张真实退化图像的RealIR-Bench基准测试集，并定制了聚焦退化消除与一致性保持的评估指标。大量实验表明，我们的模型在开源方法中排名第一，达到了最先进的性能水平。

English

Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often limited by the scale and distribution of their training data, resulting in poor generalization to real-world scenarios. Recently, large-scale image editing models have shown strong generalization ability in restoration tasks, especially for closed-source models like Nano Banana Pro, which can restore images while preserving consistency. Nevertheless, achieving such performance with those large universal models requires substantial data and computational costs. To address this issue, we construct a large-scale dataset covering nine common real-world degradation types and train a state-of-the-art open-source model to narrow the gap with closed-source alternatives. Furthermore, we introduce RealIR-Bench, which contains 464 real-world degraded images and tailored evaluation metrics focusing on degradation removal and consistency preservation. Extensive experiments demonstrate our model ranks first among open-source methods, achieving state-of-the-art performance.

RealRestorer：基于大规模图像编辑模型的通用真实世界图像修复研究

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

摘要

Support