🚩 Accepted by ICML2025

Jue Gong, Jingkai Wang, Zheng Chen, Xing Liu, Hong Gu, Yulun Zhang, Xiaokang Yang

"A new benchmark and the first one-step diffusion model for human body restoration.", 2025

• 2025-02-05: This repo is released.
• 2025-05-01: 🎉 Congratulations! OSDHuman has been accepted to ICML 2025.
• 2025-05-04: 🧪 Released the test and validation sets proposed in the paper.

Abstract: Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark datasets. In this study, we propose a high-quality dataset automated cropping and filtering (HQ-ACF) pipeline. This pipeline leverages existing object detection datasets and other unlabeled images to automatically crop and filter high-quality human images. Using this pipeline, we constructed a person-based restoration with sophisticated objects and natural activities (PERSONA) dataset, which includes training, validation, and test sets. The dataset significantly surpasses other human-related datasets in both quality and content richness. Finally, we propose OSDHuman, a novel one-step diffusion model for human body restoration. Specifically, we propose a high-fidelity image embedder (HFIE) as the prompt generator to better guide the model with low-quality human image information, effectively avoiding misleading prompts. Experimental results show that OSDHuman outperforms existing methods in both visual quality and quantitative metrics.

• Release code and pretrained models
• Release PERSONA dataset

• PERSONA Training Set
• PERSONA Test and Validation Set
• Models
• Testing
• Training
• Results
• Citation
• Acknowledgements

We provide three sets for evaluation, including both high- and low-quality validation images, and a real-world test set.

The model OSDHuman achieved state-of-the-art performance on both the datasets PERSONA-Val and PERSONA-Test. Detailed results can be found in the paper.

If you find the code helpful in your research or work, please cite the following paper(s).

@inproceedings{gong2025osdhuman,
    title={Human Body Restoration with One-Step Diffusion Model and A New Benchmark},
    author={Gong, Jue and Wang, Jingkai and Chen, Zheng and Liu, Xing and Gu, Hong and Zhang, Yulun and Yang, Xiaokang},
    booktitle={ICML},
    year={2025}
}

[TBD]