TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation
This addresses a limitation in face restoration for applications like historical restoration or missing-person retrieval, where reference images may not be age-aligned, representing a novel method for a known bottleneck.
The paper tackles the problem of face restoration when only cross-age reference images are available, which existing methods fail to handle, and proposes TimeWeaver, a framework that achieves restorations with identity fidelity and age consistency, surpassing existing methods in visual quality, identity preservation, and age consistency.
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.