Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107134
Title: | Unsupervised real image super-resolution via generative Variational AutoEncoder | Authors: | Liu, ZS Siu, WC Wang, LW Li, CT Cani, MP Chan, YL |
Issue Date: | 2020 | Source: | In Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 14-19 June 2020, Seattle, WA, USA, p. 1788-1797 | Abstract: | Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image with high fidelity or better perceptual quality. Due to the lack of ground truth images in real life, people prefer a photo-realistic image with low fidelity to a blurry image with high fidelity. In this paper, we revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution. Given that real images contain various noise and artifacts, we propose a joint image denoising and super-resolution model via Variational AutoEncoder. We come up with a conditional variational autoencoder to encode the reference for dense feature vector which can then be transferred to the decoder for target image denoising. With the aid of the discriminator, an additional overhead of super-resolution subnetwork is attached to super-resolve the denoised image with photo-realistic visual quality. We participated the NTIRE2020 Real Image Super-Resolution Challenge [24]. Experimental results show that by using the proposed approach, we can obtain enlarged images with clean and pleasant features compared to other supervised methods. We also compared our approach with state-of-the-art methods on various datasets to demonstrate the efficiency of our proposed unsupervised super-resolution model. | Publisher: | Institute of Electrical and Electronics Engineers | ISBN: | 978-1-7281-9360-1 (Electronic) 978-1-7281-9361-8 (Print on Demand(PoD)) |
DOI: | 10.1109/CVPRW50498.2020.00229 | Description: | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 14-19 June 2020, Seattle, WA, USA | Rights: | ©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The following publication Z. -S. Liu, W. -C. Siu, L. -W. Wang, C. -T. Li, M. -P. Cani and Y. -L. Chan, "Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 1788-1797 is available at https://doi.org/10.1109/CVPRW50498.2020.00229. |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Liu_Unsupervised_Real_Image.pdf | Pre-Published version | 1.17 MB | Adobe PDF | View/Open |
Page views
2
Citations as of Jun 30, 2024
SCOPUSTM
Citations
24
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
15
Citations as of Jun 27, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.