HonestFace: Towards Honest Face Restoration with One-Step Diffusion Model

TL;DR

HonestFace introduces a one-step diffusion model for face restoration that emphasizes identity preservation and texture realism, utilizing an identity embedder, masked face alignment, and a new landmark-based evaluation metric to outperform existing methods.

Contribution

The paper presents HonestFace, a novel face restoration approach that integrates identity preservation, detailed texture enhancement, and a new evaluation metric within a one-step diffusion framework.

Findings

Outperforms state-of-the-art face restoration methods in visual quality.

Achieves higher quantitative scores in fidelity and realism.

Effectively preserves identity and fine details in restored faces.

Abstract

Face restoration has achieved remarkable advancements through the years of development. However, ensuring that restored facial images exhibit high fidelity, preserve authentic features, and avoid introducing artifacts or biases remains a significant challenge. This highlights the need for models that are more "honest" in their reconstruction from low-quality inputs, accurately reflecting original characteristics. In this work, we propose HonestFace, a novel approach designed to restore faces with a strong emphasis on such honesty, particularly concerning identity consistency and texture realism. To achieve this, HonestFace incorporates several key components. First, we propose an identity embedder to effectively capture and preserve crucial identity features from both the low-quality input and multiple reference faces. Second, a masked face alignment method is presented to enhance fine-grained details and textural authenticity, thereby preventing the generation of patterned or overly synthetic textures and improving overall clarity. Furthermore, we present a new landmark-based evaluation metric. Based on affine transformation principles, this metric improves the accuracy compared to conventional L2 distance calculations for facial feature alignment. Leveraging these contributions within a one-step diffusion model framework, HonestFace delivers exceptional restoration results in terms of facial fidelity and realism. Extensive experiments demonstrate that our approach surpasses existing state-of-the-art methods, achieving superior performance in both visual quality and quantitative assessments. The code and pre-trained models will be made publicly available at https://github.com/jkwang28/HonestFace .