OSDFace: One-Step Diffusion Model for Face Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jingkai, Gong, Jue, Zhang, Lin, Chen, Zheng, Liu, Xing, Gu, Hong, Liu, Yutong, Zhang, Yulun, Yang, Xiaokang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915932539977728
author Wang, Jingkai
Gong, Jue
Zhang, Lin
Chen, Zheng
Liu, Xing
Gu, Hong
Liu, Yutong
Zhang, Yulun
Yang, Xiaokang
author_facet Wang, Jingkai
Gong, Jue
Zhang, Lin
Chen, Zheng
Liu, Xing
Gu, Hong
Liu, Yutong
Zhang, Yulun
Yang, Xiaokang
contents Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject's identity. In this work, we propose OSDFace, a novel one-step diffusion model for face restoration. Specifically, we propose a visual representation embedder (VRE) to better capture prior information and understand the input face. In VRE, low-quality faces are processed by a visual tokenizer and subsequently embedded with a vector-quantized dictionary to generate visual prompts. Additionally, we incorporate a facial identity loss derived from face recognition to further ensure identity consistency. We further employ a generative adversarial network (GAN) as a guidance model to encourage distribution alignment between the restored face and the ground truth. Experimental results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics, generating high-fidelity, natural face images with high identity consistency. The code and model will be released at https://github.com/jkwang28/OSDFace.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17163
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OSDFace: One-Step Diffusion Model for Face Restoration
Wang, Jingkai
Gong, Jue
Zhang, Lin
Chen, Zheng
Liu, Xing
Gu, Hong
Liu, Yutong
Zhang, Yulun
Yang, Xiaokang
Computer Vision and Pattern Recognition
Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject's identity. In this work, we propose OSDFace, a novel one-step diffusion model for face restoration. Specifically, we propose a visual representation embedder (VRE) to better capture prior information and understand the input face. In VRE, low-quality faces are processed by a visual tokenizer and subsequently embedded with a vector-quantized dictionary to generate visual prompts. Additionally, we incorporate a facial identity loss derived from face recognition to further ensure identity consistency. We further employ a generative adversarial network (GAN) as a guidance model to encourage distribution alignment between the restored face and the ground truth. Experimental results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics, generating high-fidelity, natural face images with high identity consistency. The code and model will be released at https://github.com/jkwang28/OSDFace.
title OSDFace: One-Step Diffusion Model for Face Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17163