TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation

2026-03-23

AI Summary

This work addresses the challenge of reference-based face restoration in cross-age scenarios—such as historical photo enhancement or missing-person identification—where existing methods struggle to simultaneously preserve identity fidelity and accurately reflect the target age due to their reliance on age-matched references. To overcome this limitation, we propose TimeWeaver, the first framework enabling cross-age reference-guided face restoration. TimeWeaver disentangles identity and age representations, learning age-robust identity features during training and incorporating a fine-tuning-free age prompting mechanism at inference to precisely control output age semantics. Key technical components include a Transformer-based ID-Fusion module, Age-Aware Gradient Guidance, and Token-Targeted Attention Boost. Extensive experiments demonstrate that TimeWeaver significantly outperforms state-of-the-art methods in visual quality, identity preservation, and age consistency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent progress in face restoration has shifted from visual fidelity to identity fidelity, driving a transition from reference-free to reference-based paradigms that condition restoration on reference images of the same person. However, these methods assume the reference and degraded input are age-aligned. When only cross-age references are available, as in historical restoration or missing-person retrieval, they fail to maintain age fidelity. To address this limitation, we propose TimeWeaver, the first reference-based face restoration framework supporting cross-age references. Given arbitrary reference images and a target-age prompt, TimeWeaver produces restorations with both identity fidelity and age consistency. Specifically, we decouple identity and age conditioning across training and inference. During training, the model learns an age-robust identity representation by fusing a global identity embedding with age-suppressed facial tokens via a transformer-based ID-Fusion module. During inference, two training-free techniques, Age-Aware Gradient Guidance and Token-Targeted Attention Boost, steer sampling toward desired age semantics, enabling precise adherence to the target-age prompt. Extensive experiments show that TimeWeaver surpasses existing methods in visual quality, identity preservation, and age consistency.

Problem

• face restoration
• cross-age reference
• identity preservation
• age consistency
• reference-based

Innovation

• cross-age face restoration
• identity preservation
• age consistency
• reference-based restoration
• transformer-based fusion