Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner

Name: Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner
Author: Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

İsim	Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner
Yazar	Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan
Basım Tarihi:	2020-04-14
Basım Yeri	- The ACM Digital Library
Konu	Deep learning, Fashion analysis, Generative learning, Image inpainting, Image reconstruction, Multi-modal neural networks
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-145037749-2
Kayıt Numarası	c1669139-45d4-4fdd-abb4-1e21831f78a4
Lokasyon	Computer Science
Tarih	2020-04-14
Örnek Metin	Inpainting a particular missing region in an image is a challenging vision task, and promising improvements on this task have been achieved with the help of the recent developments in vision-related deep learning studies. Although it may have a direct impact on the decisions of AI-based fashion analysis systems, a limited number of studies for image inpainting have been done in fashion domain, so far. In this study, we propose a multi-modal generative deep learning approach for filling the missing parts in fashion images by constraining visual features with textual features extracted from image descriptions. Our model is composed of four main blocks which can be introduced as textual feature extractor, coarse image generator guided by textual features, fine image generator enhancing the coarse output, and lastly global and local discriminators improving refined outputs. Several experiments conducted on FashionGen dataset with different combination of neural network components show that our multi-modal approach is able to generate visually plausible patches to fill the missing parts in the images.
DOI	10.1145/3397125.3397155

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner

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

Basım Tarihi 2020-04-14

Basım Yeri - The ACM Digital Library

Konu Deep learning, Fashion analysis, Generative learning, Image inpainting, Image reconstruction, Multi-modal neural networks

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-145037749-2

Kayıt Numarası c1669139-45d4-4fdd-abb4-1e21831f78a4

Lokasyon Computer Science

Tarih 2020-04-14

Örnek Metin Inpainting a particular missing region in an image is a challenging vision task, and promising improvements on this task have been achieved with the help of the recent developments in vision-related deep learning studies. Although it may have a direct impact on the decisions of AI-based fashion analysis systems, a limited number of studies for image inpainting have been done in fashion domain, so far. In this study, we propose a multi-modal generative deep learning approach for filling the missing parts in fashion images by constraining visual features with textual features extracted from image descriptions. Our model is composed of four main blocks which can be introduced as textual feature extractor, coarse image generator guided by textual features, fine image generator enhancing the coarse output, and lastly global and local discriminators improving refined outputs. Several experiments conducted on FashionGen dataset with different combination of neural network components show that our multi-modal approach is able to generate visually plausible patches to fill the missing parts in the images.

DOI 10.1145/3397125.3397155