Saved in:
Bibliographic Details
Main Authors: Song, Teer, Zhang, Yue, Tian, Yu, Wang, Ziyang, Zhang, Xianlin, Zhang, Guixuan, Liu, Xuan, Li, Xueming, Zhang, Yasen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22701
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915886027243520
author Song, Teer
Zhang, Yue
Tian, Yu
Wang, Ziyang
Zhang, Xianlin
Zhang, Guixuan
Liu, Xuan
Li, Xueming
Zhang, Yasen
author_facet Song, Teer
Zhang, Yue
Tian, Yu
Wang, Ziyang
Zhang, Xianlin
Zhang, Guixuan
Liu, Xuan
Li, Xueming
Zhang, Yasen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22701
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation
Song, Teer
Zhang, Yue
Tian, Yu
Wang, Ziyang
Zhang, Xianlin
Zhang, Guixuan
Liu, Xuan
Li, Xueming
Zhang, Yasen
Computer Vision and Pattern Recognition
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.
title TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.22701