2021
DOI: 10.3390/app11041464
|View full text |Cite
|
Sign up to set email alerts
|

Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data

Abstract: There are various challenging issues in automating line art colorization. In this paper, we propose a GAN approach incorporating semantic segmentation image data. Our GAN-based method, named Seg2pix, can automatically generate high quality colorized images, aiming at computerizing one of the most tedious and repetitive jobs performed by coloring workers in the webtoon industry. The network structure of Seg2pix is mostly a modification of the architecture of Pix2pix, which is a convolution-based generative adve… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 11 publications
(2 citation statements)
references
References 31 publications
0
2
0
Order By: Relevance
“…A colorization network can be trained on line drawings with a small domain gap using this method. Seg2pix 14 colorizes line drawings without hints, but the method must create a dataset for each character illustration and train a network with the dataset.…”
Section: Related Workmentioning
confidence: 99%
“…A colorization network can be trained on line drawings with a small domain gap using this method. Seg2pix 14 colorizes line drawings without hints, but the method must create a dataset for each character illustration and train a network with the dataset.…”
Section: Related Workmentioning
confidence: 99%
“…Another branch in the few-shot [18] relation classification field is metric-learning-based methods, which embed the samples into a metric space so that the samples can be classified according to similarity to or distance between each other. Relation network [19] adapted the convolutional neural network to extract the features of support and query samples, and the relation classification scores were obtained by concatenating the vectors of support and query samples into the relation network.…”
Section: Few-shot Relation Classificationmentioning
confidence: 99%