Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.contributor.advisor | Chi, Zheru (EIE) | en_US |
| dc.creator | Chen, Shengyang | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/11180 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Photo inpainting with GAN models | en_US |
| dcterms.abstract | Photo inpainting is an important task in photo editing. Its purpose is to recover the corrupted photos. Many methods have been proposed to solve different kinds of photo inpainting problems. The Context Encoder (CE) is the one of the most important ANN based methods. However, its performance is not very good because it may generate contents which are not semantically coherent enough. In this dissertation, I introduce my method of integrating the dilation convolution into the original context encoder to improve the photo inpainting performance. The performance evaluation is done by using not only MSE and PSNR, but also SSIM to measure the similarity between the generated content and the original content. | en_US |
| dcterms.extent | iv, 35 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Photography -- Digital techniques | en_US |
| dcterms.LCSH | Image processing -- Digital techniques | en_US |
| dcterms.LCSH | Image reconstruction | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5655.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 981.39 kB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11180