Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/81662
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 | Size | Format | |
---|---|---|---|---|
Liu_Reference_Face_Super-Resolution.pdf | 3.22 MB | Adobe PDF | View/Open |
Page views
54
Last Week
0
0
Last month
Citations as of Jun 4, 2023
Downloads
239
Citations as of Jun 4, 2023
SCOPUSTM
Citations
11
Citations as of Jun 1, 2023
WEB OF SCIENCETM
Citations
7
Citations as of Jun 1, 2023

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