Human Body Restoration with One-Step Diffusion Model and A New Benchmark
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910011851014144 |
|---|---|
| author | Gong, Jue Wang, Jingkai Chen, Zheng Liu, Xing Gu, Hong Zhang, Yulun Yang, Xiaokang |
| author_facet | Gong, Jue Wang, Jingkai Chen, Zheng Liu, Xing Gu, Hong Zhang, Yulun Yang, Xiaokang |
| contents | 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 (\emph{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 \emph{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. The dataset and code will at https://github.com/gobunu/OSDHuman. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01411 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Human Body Restoration with One-Step Diffusion Model and A New Benchmark Gong, Jue Wang, Jingkai Chen, Zheng Liu, Xing Gu, Hong Zhang, Yulun Yang, Xiaokang Computer Vision and Pattern Recognition 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 (\emph{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 \emph{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. The dataset and code will at https://github.com/gobunu/OSDHuman. |
| title | Human Body Restoration with One-Step Diffusion Model and A New Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.01411 |