Grayscale Image Colorization with GAN and CycleGAN in Different Image Domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Chen, Sheng, Yunchen, Mo, Yichen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910304437272576
author Liang, Chen
Sheng, Yunchen
Mo, Yichen
author_facet Liang, Chen
Sheng, Yunchen
Mo, Yichen
contents Automatic colorization of grayscale image has been a challenging task. Previous research have applied supervised methods in conquering this problem [ 1]. In this paper, we reproduces a GAN-based coloring model, and experiments one of its variant. We also proposed a CycleGAN based model and experiments those methods on various datasets. The result shows that the proposed CycleGAN model does well in human-face coloring and comic coloring, but lack the ability to diverse colorization.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11425
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Grayscale Image Colorization with GAN and CycleGAN in Different Image Domain
Liang, Chen
Sheng, Yunchen
Mo, Yichen
Computer Vision and Pattern Recognition
Machine Learning
I.4.3
Automatic colorization of grayscale image has been a challenging task. Previous research have applied supervised methods in conquering this problem [ 1]. In this paper, we reproduces a GAN-based coloring model, and experiments one of its variant. We also proposed a CycleGAN based model and experiments those methods on various datasets. The result shows that the proposed CycleGAN model does well in human-face coloring and comic coloring, but lack the ability to diverse colorization.
title Grayscale Image Colorization with GAN and CycleGAN in Different Image Domain
topic Computer Vision and Pattern Recognition
Machine Learning
I.4.3
url https://arxiv.org/abs/2401.11425