---

license: cc-by-nc-nd-4.0

📰 News

• 2026-06-01: Released the paper.
• 2026-05-28: Released the GGT-100K dataset, baseline training code, and checkpoints.

---

Demo. Comparing the LQ-GT pairs from GGT-100K. (You can slide it on the Project Page).

Overview of GGT-100K.

GGT-100K significantly improves the generalization capability of the models to real-world degradations.

📌 Quick Links

• 📰 News
• 🧰 Download GGT-100K Dataset
• 🏗️ Construction Process of GGT-100K (including Restoration Evaluation of SOTA MFMs)
• 🖼️ Experimental Results
• 📮 Contact
• 📚 Citation

🧰 Download GGT-100K Dataset

Download links

• Hugging Face
• Baidu Disk (password: f38z)

Expected file structure

The download links contain three parts:

• GGT-100K: the main paired dataset.
• existing-dataset: external/previous datasets used in our paper. We recommend downloading and using it together with GGT-100K for training.
• pretrained-models: pretrained checkpoints for baseline models, including 10 models × 2 settings (20 checkpoints in total): trained on existing data only vs. trained on existing data + GGT-100K.

We provide three JSONL files that list paired paths using relative file paths (relative to the dataset root), for convenient baseline usage:

• Train (existing data, without GGT-100K): train_existing.jsonl
• Train (existing data + GGT-100K): train_existing_GGT.jsonl
• Test (GGT-100K-500): test_GGT_500.jsonl

Each line is a pair:

{"gt":"relative/path/to/GT.png","lq":"relative/path/to/LQ.png","prompt":""}

Note: Among the baseline methods in this project, only Qwen-Image-Edit (qwen-image-edit) uses the prompt field. For other methods, prompt can be left empty.

When using these lists, you should join the relative paths with your local dataset root directory.

License

This dataset is released under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license: License text

---

🏗️ Construction Process of GGT-100K

Click to expand construction details

GGT-100K is constructed by these four steps.

Restoration evaluation of MFMs

We evaluate existing MFMs and report the quantitative results below.

---

🖼️ Experimental Results

Click to expand experimental results

To demonstrate the effectiveness of GGT-100K, we train 10 restoration models with and without GGT-100K, and report quantitative and visual results.

Quantitative comparison

Visual comparison

---

📮 Contact

If you have any questions, please feel free to contact: xiangtao.kong@connect.polyu.hk

📚 Citation

@article{kong2026GGT-100K,
  title={GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration},
  author={Kong, Xiangtao and Zhao, Jixin and Sun, Lingchen and Wu, Rongyuan and Zhang, Lei},
  journal={arXiv preprint arXiv:2605.31039},
  year={2026}
}