A benchmark for inpainting of clothing images with irregular holes

Name: A benchmark for inpainting of clothing images with irregular holes
Author: Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

İsim	A benchmark for inpainting of clothing images with irregular holes
Yazar	Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan
Basım Tarihi:	2020
Basım Yeri	- Springer
Konu	Dilated convolutions, Fashion image understanding, Image inpainting, Partial convolutions
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-303066822-8
Kayıt Numarası	642dd0bf-9180-4acd-b4ae-5cc7019cc6ce
Lokasyon	Computer Science
Tarih	2020
Örnek Metin	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

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

A benchmark for inpainting of clothing images with irregular holes

Yazar Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

Basım Tarihi 2020

Basım Yeri - Springer

Konu Dilated convolutions, Fashion image understanding, Image inpainting, Partial convolutions

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-303066822-8

Kayıt Numarası 642dd0bf-9180-4acd-b4ae-5cc7019cc6ce

Lokasyon Computer Science

Tarih 2020

Örnek Metin 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