Research

Paper

AI LLM February 26, 2026

Face Time Traveller : Travel Through Ages Without Losing Identity

Authors

Purbayan Kar, Ayush Ghadiya, Vishal Chudasama, Pankaj Wasnik, C. V. Jawahar

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.

Metadata

arXiv ID: 2602.22819
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-26
Fetched: 2026-02-27 04:35

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22819v1</id>\n    <title>Face Time Traveller : Travel Through Ages Without Losing Identity</title>\n    <updated>2026-02-26T10:01:37Z</updated>\n    <link href='https://arxiv.org/abs/2602.22819v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22819v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-26T10:01:37Z</published>\n    <arxiv:comment>Accepted at CVPR 2026 (Findings Track)</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Purbayan Kar</name>\n    </author>\n    <author>\n      <name>Ayush Ghadiya</name>\n    </author>\n    <author>\n      <name>Vishal Chudasama</name>\n    </author>\n    <author>\n      <name>Pankaj Wasnik</name>\n    </author>\n    <author>\n      <name>C. V. Jawahar</name>\n    </author>\n  </entry>"
}