Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration
This addresses the problem of restoring degraded old face photos for preservation applications, representing an incremental improvement over prior diffusion-based methods.
The paper tackles old-photo face restoration by proposing SSDiff, a self-supervised selective-guided diffusion model that uses pseudo-reference faces for region-specific restoration, outperforming existing methods on perceptual quality and fidelity with a new 300-image benchmark.
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.