Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/29613
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Islam, T | - |
dc.contributor.author | Miron, A | - |
dc.contributor.author | Liu, X | - |
dc.contributor.author | Li, Y | - |
dc.date.accessioned | 2024-08-27T11:38:08Z | - |
dc.date.available | 2024-08-27T11:38:08Z | - |
dc.date.issued | 2024-08-16 | - |
dc.identifier | ORCiD: Tasin Islam https://orcid.org/0000-0001-7568-9322 | - |
dc.identifier | ORCiD: Alina Miron https://orcid.org/0000-0002-0068-4495 | - |
dc.identifier | ORCiD: Xiaohui Liu https://orcid.org/0000-0003-1589-1267 | - |
dc.identifier | ORCiD: Yongmin Li https://orcid.org/0000-0003-1668-2440 | - |
dc.identifier | 117189 | - |
dc.identifier.citation | Islam, T. et al. (2024) 'Image-based virtual try-on: Fidelity and simplification', Signal Processing: Image Communication, 129, 117189, pp. 1 - 15. doi: 10.1016/j.image.2024.117189. | en_US |
dc.identifier.issn | 0923-5965 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/29613 | - |
dc.description | Data availability: I have shared a link to my code and dataset via GitHub. | en_US |
dc.description.abstract | We introduce a novel image-based virtual try-on model designed to replace a candidate’s garment with a desired target item. The proposed model comprises three modules: segmentation, garment warping, and candidate-clothing fusion. Previous methods have shown limitations in cases involving significant differences between the original and target clothing, as well as substantial overlapping of body parts. Our model addresses these limitations by employing two key strategies. Firstly, it utilises a candidate representation based on an RGB skeleton image to enhance spatial relationships among body parts, resulting in robust segmentation and improved occlusion handling. Secondly, truncated U-Net is employed in both the segmentation and warping modules, enhancing segmentation performance and accelerating the try-on process. The warping module leverages an efficient affine transform for ease of training. Comparative evaluations against state-of-the-art models demonstrate the competitive performance of our proposed model across various scenarios, particularly excelling in handling occlusion cases and significant differences in clothing cases. This research presents a promising solution for image-based virtual try-on, advancing the field by overcoming key limitations and achieving superior performance. | en_US |
dc.description.sponsorship | Engineering and Physical Sciences Research Council (EPSRC) grant number EP/T518116/1. | en_US |
dc.format.extent | 1 - 15 | - |
dc.format.medium | Print-Electronic | - |
dc.language | English | - |
dc.language.iso | en_US | en_US |
dc.publisher | Elsevier | en_US |
dc.rights | Copyright © 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/ ). | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | virtual try-on (VTON) | en_US |
dc.subject | generative adversarial network (GAN) | en_US |
dc.subject | fashion synthesis | en_US |
dc.subject | occlusion-handling | en_US |
dc.subject | e-commerce | en_US |
dc.title | Image-based virtual try-on: Fidelity and simplification | en_US |
dc.type | Article | en_US |
dc.date.dateAccepted | 2024-07-27 | - |
dc.identifier.doi | https://doi.org/10.1016/j.image.2024.117189 | - |
dc.relation.isPartOf | Signal Processing: Image Communication | - |
pubs.publication-status | Published | - |
pubs.volume | 129 | - |
dc.identifier.eissn | 1879-2677 | - |
dc.rights.license | https://creativecommons.org/licenses/by/4.0/ legalcode.en | - |
dc.rights.holder | The Authors | - |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/ ). | 3.79 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License