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

TL;DR

TimeWeaver is a novel face restoration framework that maintains both identity and age consistency when using cross-age reference images, addressing a key limitation in current methods.

Contribution

It introduces a cross-age reference-based face restoration method with age-robust identity representation and training-free age steering techniques.

Findings

Outperforms existing methods in visual quality and identity preservation.

Achieves strong age consistency with cross-age references.

Supports arbitrary reference images and target ages.

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.