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

Abstract

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.

Figures (15)

• Figure 1: RealRestorer effectively restores diverse real-world image degradations, including deblurring, moiré pattern removal, compression restoration, reflection removal, hazing removal, rain removal, deflare, and low-light enhancement.
• Figure 2: Overview of our large-scale Synthetic Degradation Data pipeline. We construct nine representative degradation types, including blur, compression artifacts, moiré patterns, low-light, noise, flare, reflection, haze, and rain. Compared with previous synthetic-only pipelines, our upgraded framework incorporates granular noise modeling, segment-aware perturbations, and web-style degradation processes, significantly narrowing the gap between synthetic and real-world distributions. This comprehensive pipeline enables more robust and generalizable restoration learning.
• Figure 3: Comparison with state-of-the-art image editing models across nine real-world degradations, including blur, compression artifacts, moiré patterns, low-light, noise, flare, reflection, haze, and rain. We compare our method with large-scale image editing models, such as Seedream 4.5, Nano Banana Pro, GPT-Image-1.5, Step1X-Edit, FLUX.1-Kontext-dev, Qwen-Image-Edit-2511, and LongCat-Image-Edit.
• Figure 4: Model performance with varying training steps and training data on RealIR-Bench. The blue line shows transfer training on synthetic degradation data, where the model gradually acquires basic restoration capability. The blue dashed line indicates performance degradation after prolonged training due to the limited diversity of synthetic data. The purple line represents supervised fine-tuning with real-world degradation data, which rapidly improves performance and generalization. The purple dashed segment indicates the onset of overfitting after around 2.5K steps.
• Figure 5: Examples from our training dataset containing both synthetic and real-world degradation pairs. The upper rows with gray labels show synthesized degradations generated by our pipeline, while the bottom rows highlighted with orange labels correspond to real-world degraded images paired with clean references.