GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration
:::info Stub — Full Engineering Breakdown Coming This paper has a linked code implementation and was featured on Hugging Face Papers with 30 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Xiangtao Kong et al. |
| Year | 2026 |
| HF Upvotes | 30 |
| arXiv | 2605.31039 |
| Download | |
| Code | https://github.com/PolyU-VCLab/GGT-100K |
Abstract
Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models.
Engineering Breakdown
The Problem
Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture.
The Approach
In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images.
Key Results
We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Generative
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::