Author
Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan
Publication Date
2020
Publication Place
-
Springer
Subject
Dilated convolutions, Fashion image understanding, Image inpainting, Partial convolutions
Type
Document
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
978-303066822-8
Record ID
642dd0bf-9180-4acd-b4ae-5cc7019cc6ce
Library Location
Computer Science
Date
2020
Sample Text
Fashion image understanding is an active research field with a large number of practical applications for the industry. Despite its practical impacts on intelligent fashion analysis systems, clothing image inpainting has not been extensively examined yet. For that matter, we present an extensive benchmark of clothing image inpainting on well-known fashion datasets. Furthermore, we introduce the use of a dilated version of partial convolutions, which efficiently derive the mask update step, and empirically show that the proposed method reduces the required number of layers to form fully-transparent masks. Experiments show that dilated partial convolutions (DPConv) improve the quantitative inpainting performance when compared to the other inpainting strategies, especially it performs better when the mask size is 20% or more of the image.
DOI
10.1007/978-3-030-66823-5_11
