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

• URL: http://arxiv.org/abs/2603.22701v1
• Date: Tue, 24 Mar 2026 01:48:27 GMT
• Title: TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation
• Abstract summary: TimeWeaver is a reference-based face restoration framework supporting cross-age references.<n>We decouple identity and age conditioning across training and inference.<n>Extensive experiments show that TimeWeaver surpasses existing methods in visual quality, identity preservation, and age consistency.
• Score: 24.354251784441217
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Vera: Identity-Faithful Human Subject-to-Video Generation [66.45205582225942]
  We propose Vera, a unified human-centric S2V framework for single- and multi-person generation.<n>We first construct a million-pair identity-aligned human image-video dataset through person-level cross-clip retrieval.<n>We show that Vera improves human identity consistency, multi-person subject binding, and motion naturalness, while reducing identity confusion and excessive reference-image copying.
  arXiv  Detail & Related papers  (2026-07-22T15:08:30Z)
• Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation [79.94088803584262]
  Identity-preserving video generation (IPVG) aims to synthesize high-fidelity videos that follow text prompts while preserving a reference identity.<n>We propose ST-DRC, an effective Spatial-Temporal Decoupled Reference Conditioning framework for identity-preserving text-to-video generation.<n>We show that ST-DRC achieves strong identity preservation, prompt alignment, temporal consistency, and video quality with a lightweight design built on LTX-2.3.
  arXiv  Detail & Related papers  (2026-06-01T16:12:18Z)
• IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration [2.7652581048436864]
  Blind face restoration is highly ill-posed under severe degradation.<n>Same-identity references reduce this ambiguity, but mismatched pose, expression, illumination, age, makeup, or local facial states can lead to overuse of reference appearance.<n>We propose textbfIConFace, a unified reference-aware and no-reference framework with identity--structure asymmetric conditioning.
  arXiv  Detail & Related papers  (2026-05-04T16:49:51Z)
• MeInTime: Bridging Age Gap in Identity-Preserving Face Restoration [24.354251784441217]
  MeInTime is a diffusion-based face restoration method that extends reference-based restoration from same-age to cross-age settings.<n>Given one or few reference images along with an age prompt corresponding to the degraded input, MeInTime achieves faithful restoration with both identity fidelity and age consistency.
  arXiv  Detail & Related papers  (2026-03-19T09:11:07Z)
• Face Time Traveller : Travel Through Ages Without Losing Identity [22.930701520656005]
  Face Time Traveller (FaceTT) is a diffusion-based framework that achieves high-fidelity, identity-consistent age transformation.<n>A tuning-free Angular Inversion method is proposed that efficiently maps real faces into the diffusion latent space for fast and accurate reconstruction.<n>Experiments on benchmark datasets and in-the-wild testset demonstrate that FaceTT achieves superior identity retention, background preservation and aging realism.
  arXiv  Detail & Related papers  (2026-02-26T10:01:37Z)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models [39.98150173094697]
  AgeBooth produces identity-consistent face images across different ages from a single reference image.<n> Experiments show that AgeBooth achieves superior age control and visual quality compared to previous state-of-the-art editing-based methods.
  arXiv  Detail & Related papers  (2025-10-07T09:25:09Z)
• Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space [4.852932390076274]
  We propose to synthesize aged and de-aged faces via editing latent space of StyleGAN2.<n>We then propose a formula for estimating the limits on aging/de-aging parameters that ensures identity preservation for a given input face.<n>Our method and estimated parameters can be used for benchmarking cross-age face recognition, age assurance systems, or systems for detection of synthetic images.
  arXiv  Detail & Related papers  (2025-08-12T10:02:42Z)
• From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging [23.367023983827156]
  Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare.<n>The core challenge lies in balancing age accuracy and identity preservation.<n>We propose a two-pass face aging framework, named Cradle2Cane, based on few-step text-to-image (T2I) diffusion models.
  arXiv  Detail & Related papers  (2025-06-26T03:48:28Z)
• Reference-Guided Identity Preserving Face Restoration [54.10295747851343]
  Preserving face identity is a critical yet persistent challenge in diffusion-based image restoration.<n>This paper introduces a novel approach that maximizes reference face utility for improved face restoration and identity preservation.
  arXiv  Detail & Related papers  (2025-05-28T02:46:34Z)
• When StyleGAN Meets Stable Diffusion: a $\mathscr{W}_+$ Adapter for Personalized Image Generation [60.305112612629465]
  Text-to-image diffusion models have excelled in producing diverse, high-quality, and photo-realistic images. We present a novel use of the extended StyleGAN embedding space $mathcalW_+$ to achieve enhanced identity preservation and disentanglement for diffusion models. Our method adeptly generates personalized text-to-image outputs that are not only compatible with prompt descriptions but also amenable to common StyleGAN editing directions.
  arXiv  Detail & Related papers  (2023-11-29T09:05:14Z)
• A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks [54.57520952117123]
  Biphasic facial age translation aims at predicting the appearance of the input face at any age. We propose a unified framework for biphasic facial age translation with noisy-semantic guided generative adversarial networks.
  arXiv  Detail & Related papers  (2021-09-15T15:30:35Z)
• Age Gap Reducer-GAN for Recognizing Age-Separated Faces [72.26969872180841]
  We propose a novel algorithm for matching faces with temporal variations caused due to age progression. The proposed generative adversarial network algorithm is a unified framework that combines facial age estimation and age-separated face verification.
  arXiv  Detail & Related papers  (2020-11-11T16:43:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.