Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/81662
PIRA download icon_1.1View/Download Full Text
Title: Reference based face super-resolution
Authors: Liu, ZS 
Siu, WC 
Chan, YL 
Issue Date: 2019
Source: IEEE access, 2019, v. 7, p. 129112-129126
Abstract: Despite the great progress of image super-resolution in recent years, face super-resolution has still much room to explore good visual quality while preserving original facial attributes for larger up-scaling factors. This paper investigates a new research direction in face super-resolution, called Reference based face Super-Resolution (RefSR), in which a reference facial image containing genuine attributes is provided in addition to the low-resolution images for super-resolution. We focus on transferring the key information extracted from reference facial images to the super-resolution process to guarantee the content similarity between the reference and super-resolution image. We propose a novel Conditional Variational AutoEncoder model for this Reference based Face Super-Resolution (RefSR-VAE). By using the encoder to map the reference image to the joint latent space, we can then use the decoder to sample the encoder results to super-resolve low-resolution facial images to generate super-resolution images with good visual quality. We create a benchmark dataset on reference based face super-resolution (RefSR-Face) for general research use, which contains reference images paired with low-resolution images of various pose, emotions, ages and appearance. Both objective and subjective evaluations were conducted, which demonstrate the great potential of using reference images for face super-resolution. By comparing it with state-of-the-art super-resolution approaches, our proposed approach also achieves superior performance.
Keywords: Face super-resolution
Deep feature extraction
Style transfer
Publisher: Institute of Electrical and Electronics Engineers
Journal: IEEE access 
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2019.2934078
Rights: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0
The following publication Z. Liu, W. Siu and Y. Chan, "Reference Based Face Super-Resolution," in IEEE Access, vol. 7, pp. 129112-129126, 2019 is available at https://dx.doi.org/10.1109/ACCESS.2019.2934078
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
Liu_Reference_Face_Super-Resolution.pdf3.22 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

49
Citations as of Jul 3, 2022

Downloads

228
Citations as of Jul 3, 2022

SCOPUSTM   
Citations

7
Citations as of Jul 7, 2022

WEB OF SCIENCETM
Citations

4
Citations as of Jul 7, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.