Face Time Traveller : Travel Through Ages Without Losing Identity

TL;DR

Face Time Traveller (FaceTT) is a diffusion-based framework that enables realistic, identity-preserving age transformations by encoding biological and environmental cues, with efficient inversion and adaptive attention mechanisms.

Contribution

The paper introduces FaceTT, a novel diffusion-based face aging model with context-aware prompt refinement, a tuning-free inversion method, and adaptive attention control for improved realism and identity preservation.

Findings

Outperforms state-of-the-art methods in identity retention.

Achieves high-fidelity age transformations with background preservation.

Demonstrates robustness on benchmark and in-the-wild datasets.

Abstract

Face aging, an ill-posed problem shaped by environmental and genetic factors, is vital in entertainment, forensics, and digital archiving, where realistic age transformations must preserve both identity and visual realism. However, existing works relying on numerical age representations overlook the interplay of biological and contextual cues. Despite progress in recent face aging models, they struggle with identity preservation in wide age transformations, also static attention and optimization-heavy inversion in diffusion limit adaptability, fine-grained control and background consistency. To address these challenges, we propose Face Time Traveller (FaceTT), a diffusion-based framework that achieves high-fidelity, identity-consistent age transformation. Here, we introduce a Face-Attribute-Aware Prompt Refinement strategy that encodes intrinsic (biological) and extrinsic (environmental) aging cues for context-aware conditioning. A tuning-free Angular Inversion method is proposed that efficiently maps real faces into the diffusion latent space for fast and accurate reconstruction. Moreover, an Adaptive Attention Control mechanism is introduced that dynamically balances cross-attention for semantic aging cues and self-attention for structural and identity preservation. Extensive experiments on benchmark datasets and in-the-wild testset demonstrate that FaceTT achieves superior identity retention, background preservation and aging realism over state-of-the-art (SOTA) methods.