用大规模数据训练开源模型，提升真实图像修复的通用性。
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
- 构建涵盖9类真实退化的数据集，训练高性能开源修复模型。
- 在464张真实退化图像上表现最佳，优于现有开源方法。
- 适合需要高通用性修复能力的研究与工业应用。
真实世界退化下的图像修复对自动驾驶、目标检测等下游任务至关重要。然而，现有修复模型受限于训练数据规模与分布，难以泛化到真实场景。近期大型图像编辑模型（如Nano Banana Pro）展现出强泛化能力，尤其在保持一致性方面表现优异，但使用这类通用大模型需巨大数据与算力成本。为此，本文构建了覆盖九类常见真实退化类型的大型数据集，并训练出当前最先进的开源修复模型，缩小与闭源模型的差距。此外，提出RealIR-Bench基准，包含464张真实退化图像及针对退化去除与一致性保持的定制评估指标。大量实验表明，本模型在开源方法中排名第一，达到领先性能。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。