{"ID":2855527,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12114","arxiv_id":"2510.12114","title":"Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration","abstract":"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.","short_abstract":"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 Sel...","url_abs":"https://arxiv.org/abs/2510.12114","url_pdf":"https://arxiv.org/pdf/2510.12114v1","authors":"[\"Wenjie Li\",\"Xiangyi Wang\",\"Heng Guo\",\"Guangwei Gao\",\"Zhanyu Ma\"]","published":"2025-10-14T03:34:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":608258,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2855527,"paper_url":"https://arxiv.org/abs/2510.12114","paper_title":"Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration","repo_url":"https://github.com/PRIS-CV/SSDiff","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}