用自监督生成伪参考图，精准修复老照片人脸的破损与褪色问题。
Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration
- 通过预训练模型生成伪参考图，提供结构与颜色先验。
- 分阶段恢复：全程结构引导，后期专注颜色优化，提升真实感。
- 支持局部修复且不改人脸身份，适合老旧影像修复场景。
老照片人脸修复因多重退化（如断裂、褪色、严重模糊）面临巨大挑战。现有基于预训练扩散模型的方法依赖显式退化先验或全局统计指导，难以处理局部伪影或人脸色彩问题。本文提出自监督选择性引导扩散模型（SSDiff），利用预训练扩散模型在弱引导下生成伪参考人脸，其具有结构对齐轮廓与自然色彩，实现分阶段监督：整个去噪过程施加结构引导，后期步骤进行颜色精修，契合扩散模型从粗到细的特性。结合人脸分割图与擦除掩码，方法可选择性修复断裂区域，避免身份错乱。我们还构建了包含300张真实老照片的VintageFace基准数据集，涵盖不同退化程度。SSDiff在感知质量、保真度和区域可控性上均优于现有基于GAN和扩散模型的方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。