Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

OSDFace: One-Step Diffusion Model for Face Restoration

About

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.

Jingkai Wang, Jue Gong, Lin Zhang, Zheng Chen, Xing Liu, Hong Gu, Yutong Liu, Yulun Zhang, Xiaokang Yang• 2024

Related benchmarks

TaskDatasetResultRank
Face RestorationCelebA synthetic (test)
LPIPS0.336
16
Face RestorationWebPhoto 43 (test)
MUSIQ73.93
7
Face RestorationWider 61 (test)
MUSIQ74.6
7
Face RestorationLFW 14 (test)
MUSIQ0.7535
7
Showing 4 of 4 rows

Other info

Follow for update