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

Source: [TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation](<https://www.sota2.com/research/paper/69c36c010636e5bf4afc6472>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T05:00:04.122Z

Authors: Teer Song, Yue Zhang, Yu Tian, Ziyang Wang, Xianlin Zhang, Guixuan Zhang, Xuan Liu, Xueming Li, Yasen Zhang

Published: 2026-03-24T01:48:27.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Face Restoration on Real-world face restoration](<https://www.sota2.com/research/sota/face-restoration-on-real-world-face-restoration.md>): Face Restoration; Real-world face restoration; NIQE: 3.84.

- [Face Restoration and Age Editing on Cross-age dataset](<https://www.sota2.com/research/sota/face-restoration-and-age-editing-on-cross-age-dataset.md>): Face Restoration and Age Editing; Cross-age dataset; PSNR: 25.11.

- [Face Restoration on Same-age synthetic (test)](<https://www.sota2.com/research/sota/face-restoration-on-same-age-synthetic-test.md>): Face Restoration; Same-age synthetic (test); PSNR: 25.5.

- [Face Restoration on Cross-age synthetic (test)](<https://www.sota2.com/research/sota/face-restoration-on-cross-age-synthetic-test.md>): Face Restoration; Cross-age synthetic (test); PSNR: 25.11.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.22701>)

[PDF](<https://arxiv.org/pdf/2603.22701.pdf>)