MeInTime: Bridging Age Gap in Identity-Preserving Face Restoration

2026-03-19

AI Summary

This work addresses the challenge of identity preservation in cross-age face restoration—particularly relevant for historical photo enhancement—where existing reference-based methods often fail due to their assumption of age consistency between input and reference images. To overcome this limitation, we propose MeInTime, a diffusion-based approach that disentangles identity and age features, enabling high-fidelity identity recovery and natural age coherence using only a few reference images and a target age prompt. Our key contributions include the first extension of reference-guided restoration to cross-age settings, a novel identity feature injection mechanism during training, and an inference strategy termed Age-Aware Gradient Guidance that requires no fine-tuning. Additionally, we introduce new attention and Gated Residual Fusion modules. Extensive experiments demonstrate that MeInTime significantly outperforms current methods in both identity fidelity and age consistency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

To better preserve an individual's identity, face restoration has evolved from reference-free to reference-based approaches, which leverage high-quality reference images of the same identity to enhance identity fidelity in the restored outputs. However, most existing methods implicitly assume that the reference and degraded input are age-aligned, limiting their effectiveness in real-world scenarios where only cross-age references are available, such as historical photo restoration. This paper proposes MeInTime, a diffusion-based face restoration method that extends reference-based restoration from same-age to cross-age settings. Given one or few reference images along with an age prompt corresponding to the degraded input, MeInTime achieves faithful restoration with both identity fidelity and age consistency. Specifically, we decouple the modeling of identity and age conditions. During training, we focus solely on effectively injecting identity features through a newly introduced attention mechanism and introduce Gated Residual Fusion modules to facilitate the integration between degraded features and identity representations. At inference, we propose Age-Aware Gradient Guidance, a training-free sampling strategy, using an age-driven direction to iteratively nudge the identity-aware denoising latent toward the desired age semantic manifold. Extensive experiments demonstrate that MeInTime outperforms existing face restoration methods in both identity preservation and age consistency. Our code is available at: https://github.com/teer4/MeInTime

Problem

• face restoration
• cross-age reference
• identity preservation
• age consistency
• historical photo restoration

Innovation

• cross-age face restoration
• identity preservation
• diffusion model
• age-aware gradient guidance
• reference-based restoration