Blind Face Restoration via Deep Multi-scale Component Dictionaries

by   Xiaoming Li, et al.

Recent reference-based face restoration methods have received considerable attention due to their great capability in recovering high-frequency details on real low-quality images. However, most of these methods require a high-quality reference image of the same identity, making them only applicable in limited scenes. To address this issue, this paper suggests a deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations. To begin with, we use K-means to generate deep dictionaries for perceptually significant face components (, left/right eyes, nose and mouth) from high-quality images. Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature transfer (DFT) block. In particular, component AdaIN is leveraged to eliminate the style diversity between the input and dictionary features (, illumination), and a confidence score is proposed to adaptively fuse the dictionary feature to the input. Finally, multi-scale dictionaries are adopted in a progressive manner to enable the coarse-to-fine restoration. Experiments show that our proposed method can achieve plausible performance in both quantitative and qualitative evaluation, and more importantly, can generate realistic and promising results on real degraded images without requiring an identity-belonging reference. The source code and models are available at <>.


page 5

page 11

page 12

page 13


Learning Dual Memory Dictionaries for Blind Face Restoration

To improve the performance of blind face restoration, recent works mainl...

Progressive Semantic-Aware Style Transformation for Blind Face Restoration

Face restoration is important in face image processing, and has been wid...

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Although generative facial prior and geometric prior have recently demon...

Learning Warped Guidance for Blind Face Restoration

This paper studies the problem of blind face restoration from an unconst...

RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs

Blind face restoration aims at recovering high-quality face images from ...

Seeing through a Black Box: Toward High-Quality Terahertz TomographicImaging via Multi-Scale Spatio-Spectral Image Fusion

Terahertz tomographic imaging has recently arisen significant attention ...

Deep Generation of Face Images from Sketches

Recent deep image-to-image translation techniques allow fast generation ...

Please sign up or login with your details

Forgot password? Click here to reset