InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Howard, Alaluf, Yuval, Ma, Sizhuo, Kadambi, Achuta, Wang, Jian, Aberman, Kfir
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910735167127552
author Zhang, Howard
Alaluf, Yuval
Ma, Sizhuo
Kadambi, Achuta
Wang, Jian
Aberman, Kfir
author_facet Zhang, Howard
Alaluf, Yuval
Ma, Sizhuo
Kadambi, Achuta
Wang, Jian
Aberman, Kfir
contents Face image restoration aims to enhance degraded facial images while addressing challenges such as diverse degradation types, real-time processing demands, and, most crucially, the preservation of identity-specific features. Existing methods often struggle with slow processing times and suboptimal restoration, especially under severe degradation, failing to accurately reconstruct finer-level identity details. To address these issues, we introduce InstantRestore, a novel framework that leverages a single-step image diffusion model and an attention-sharing mechanism for fast and personalized face restoration. Additionally, InstantRestore incorporates a novel landmark attention loss, aligning key facial landmarks to refine the attention maps, enhancing identity preservation. At inference time, given a degraded input and a small (~4) set of reference images, InstantRestore performs a single forward pass through the network to achieve near real-time performance. Unlike prior approaches that rely on full diffusion processes or per-identity model tuning, InstantRestore offers a scalable solution suitable for large-scale applications. Extensive experiments demonstrate that InstantRestore outperforms existing methods in quality and speed, making it an appealing choice for identity-preserving face restoration.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
Zhang, Howard
Alaluf, Yuval
Ma, Sizhuo
Kadambi, Achuta
Wang, Jian
Aberman, Kfir
Computer Vision and Pattern Recognition
Face image restoration aims to enhance degraded facial images while addressing challenges such as diverse degradation types, real-time processing demands, and, most crucially, the preservation of identity-specific features. Existing methods often struggle with slow processing times and suboptimal restoration, especially under severe degradation, failing to accurately reconstruct finer-level identity details. To address these issues, we introduce InstantRestore, a novel framework that leverages a single-step image diffusion model and an attention-sharing mechanism for fast and personalized face restoration. Additionally, InstantRestore incorporates a novel landmark attention loss, aligning key facial landmarks to refine the attention maps, enhancing identity preservation. At inference time, given a degraded input and a small (~4) set of reference images, InstantRestore performs a single forward pass through the network to achieve near real-time performance. Unlike prior approaches that rely on full diffusion processes or per-identity model tuning, InstantRestore offers a scalable solution suitable for large-scale applications. Extensive experiments demonstrate that InstantRestore outperforms existing methods in quality and speed, making it an appealing choice for identity-preserving face restoration.
title InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06753