WaveFace: Authentic face restoration with efficient frequency recovery
Author(s)
Miao, Yunqi
Deng, Jiankang
Han, Jungong
Type
Conference Paper
Abstract
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.
Date Issued
2024-09-16
Date Acceptance
2024-06-17
Citation
2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024, 2024, pp.6583-6592
ISBN
979-8-3503-5301-3
ISSN
1063-6919
Publisher
IEEE Computer Soc
Start Page
6583
End Page
6592
Journal / Book Title
2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024
Copyright Statement
© 2024 IEEE. This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.
Source
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Interdisciplinary Applications
Computer Science, Theory & Methods
Science & Technology
Technology
Publication Status
Published
Start Date
2024-06-16
Finish Date
2024-06-22
Coverage Spatial
Seattle, WA, USA