AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Prior

TL;DR

AuthFace introduces a face-oriented generative diffusion prior and a specialized fine-tuning pipeline to improve the authenticity and detail of blind face restoration, surpassing existing methods in real-world scenarios.

Contribution

The paper presents a novel face-oriented diffusion prior and a photography-guided fine-tuning process for more authentic and detailed face restoration.

Findings

Outperforms existing methods on synthetic and real-world datasets.

Effectively restores rich facial details with minimal artifacts.

Enhances facial feature accuracy in blind face restoration.

Abstract

Blind face restoration (BFR) is a fundamental and challenging problem in computer vision. To faithfully restore high-quality (HQ) photos from poor-quality ones, recent research endeavors predominantly rely on facial image priors from the powerful pretrained text-to-image (T2I) diffusion models. However, such priors often lead to the incorrect generation of non-facial features and insufficient facial details, thus rendering them less practical for real-world applications. In this paper, we propose a novel framework, namely AuthFace that achieves highly authentic face restoration results by exploring a face-oriented generative diffusion prior. To learn such a prior, we first collect a dataset of 1.5K high-quality images, with resolutions exceeding 8K, captured by professional photographers. Based on the dataset, we then introduce a novel face-oriented restoration-tuning pipeline that fine-tunes a pretrained T2I model. Identifying key criteria of quality-first and photography-guided annotation, we involve the retouching and reviewing process under the guidance of photographers for high-quality images that show rich facial features. The photography-guided annotation system fully explores the potential of these high-quality photographic images. In this way, the potent natural image priors from pretrained T2I diffusion models can be subtly harnessed, specifically enhancing their capability in facial detail restoration. Moreover, to minimize artifacts in critical facial areas, such as eyes and mouth, we propose a time-aware latent facial feature loss to learn the authentic face restoration process. Extensive experiments on the synthetic and real-world BFR datasets demonstrate the superiority of our approach.