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

2025-05-24

AI Summary

To address identity distortion, spurious texture generation, and bias introduction in face restoration, this paper proposes a one-step diffusion model centered on “honesty,” prioritizing identity consistency and texture fidelity. Methodologically: (1) a lightweight identity embedder enables fine-grained disentanglement of ID features; (2) a mask-guided face alignment mechanism—incorporating affine-invariant landmark distance metrics—enhances geometric fidelity; and (3) an end-to-end differentiable framework eliminates error accumulation inherent in multi-stage pipelines. Extensive evaluation on CelebA-HQ and FFHQ demonstrates significant improvements over state-of-the-art methods: +8.2% identity preservation rate, −0.021 LPIPS reduction, and notably lower FID scores. The code and pretrained models are publicly released.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Data and user privacy-enhancing technologies for the Web

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 .

Problem

• Ensuring high fidelity and authentic features in restored faces
• Avoiding artifacts and biases in face restoration models
• Improving identity consistency and texture realism in reconstructions

Innovation

• One-step diffusion model for face restoration
• Identity embedder preserves crucial facial features
• Masked face alignment enhances texture realism