Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914091375788032 |
|---|---|
| author | Li, Wenjie Wang, Xiangyi Guo, Heng Gao, Guangwei Ma, Zhanyu |
| author_facet | Li, Wenjie Wang, Xiangyi Guo, Heng Gao, Guangwei Ma, Zhanyu |
| contents | Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical guidance, which struggle with localized artifacts or face color. We propose Self-Supervised Selective-Guided Diffusion (SSDiff), which leverages pseudo-reference faces generated by a pre-trained diffusion model under weak guidance. These pseudo-labels exhibit structurally aligned contours and natural colors, enabling region-specific restoration via staged supervision: structural guidance applied throughout the denoising process and color refinement in later steps, aligned with the coarse-to-fine nature of diffusion. By incorporating face parsing maps and scratch masks, our method selectively restores breakage regions while avoiding identity mismatch. We further construct VintageFace, a 300-image benchmark of real old face photos with varying degradation levels. SSDiff outperforms existing GAN-based and diffusion-based methods in perceptual quality, fidelity, and regional controllability. Code link: https://github.com/PRIS-CV/SSDiff. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12114 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration Li, Wenjie Wang, Xiangyi Guo, Heng Gao, Guangwei Ma, Zhanyu Computer Vision and Pattern Recognition Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical guidance, which struggle with localized artifacts or face color. We propose Self-Supervised Selective-Guided Diffusion (SSDiff), which leverages pseudo-reference faces generated by a pre-trained diffusion model under weak guidance. These pseudo-labels exhibit structurally aligned contours and natural colors, enabling region-specific restoration via staged supervision: structural guidance applied throughout the denoising process and color refinement in later steps, aligned with the coarse-to-fine nature of diffusion. By incorporating face parsing maps and scratch masks, our method selectively restores breakage regions while avoiding identity mismatch. We further construct VintageFace, a 300-image benchmark of real old face photos with varying degradation levels. SSDiff outperforms existing GAN-based and diffusion-based methods in perceptual quality, fidelity, and regional controllability. Code link: https://github.com/PRIS-CV/SSDiff. |
| title | Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.12114 |