2024/03/19 by Yunqi Miao, Jiankang Deng, Miao, Yunqi +3 · 8 citations
Computer Science · Medicine · #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Face (sociological concept) #Face recognition and analysis #Facial Nerve Paralysis Treatment and Research #Linguistics #Philosophy
paper · open access · doi:10.48550/arxiv.2403.12760
published in White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (White Rose University Consortium)
openalex publication_date 2024/03/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial details. In this work, we propose WaveFace to solve the problems in the frequency domain, where low- and high-frequency components decomposed by wavelet transformation are considered individually to maximize authenticity as well as efficiency. The diffusion model is applied to recover the low-frequency component only, which presents general information of the original image but 1/16 in size. To preserve the original identity, the generation is conditioned on the low-frequency component of low-quality images at each denoising step. Meanwhile, high-frequency components at multiple decomposition levels are handled by a unified network, which recovers complex facial details in a single step. Evaluations on four benchmark datasets show that: 1) WaveFace outperforms state-of-the-art methods in authenticity, especially in terms of identity preservation, and 2) authentic images are restored with the efficiency 10x faster than existing diffusion model-based BFR methods.