End-to-End Conditional GAN-based Architectures for Image Colourisation

被引:2
|
作者
Blanch, Marc Gorriz [1 ]
Mrak, Marta [1 ]
Smeaton, Alan F. [2 ]
O'Connor, Noel E. [2 ]
机构
[1] BBC Res & Dev, London, England
[2] Dublin City Univ, Dublin, Ireland
基金
欧盟地平线“2020”;
关键词
Colourisation; Conditional GANs; CNNs;
D O I
10.1109/mmsp.2019.8901712
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image. Observing that existing colourisation methods sometimes exhibit a lack of colourfulness, this paper proposes a method to improve colourisation results. In particular, the method uses Generative Adversarial Neural Networks (GANs) and focuses on improvement of training stability to enable better generalisation in large multi-class image datasets. Additionally, the integration of instance and batch normalisation layers in both generator and discriminator is introduced to the popular U-Net architecture, boosting the network capabilities to generalise the style changes of the content. The method has been tested using the ILSVRC 2012 dataset, achieving improved automatic colourisation results compared to other methods based on GANs.
引用
收藏
页数:6
相关论文
共 50 条
  • [31] An end-to-end spike-based image compression architecture
    Doutsi, Effrosyni
    Antonini, Marc
    Tsakalides, Panagiotis
    2020 54TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2020, : 818 - 820
  • [32] End-to-end image compression method based on perception metric
    Liu, Shuai
    Huang, Yingcong
    Yang, Huoxiang
    Liang, Yongsheng
    Liu, Wei
    SIGNAL IMAGE AND VIDEO PROCESSING, 2022, 16 (07) : 1803 - 1810
  • [33] End-to-end Driving via Conditional Imitation Learning
    Codevilla, Felipe
    Mueller, Matthias
    Lopez, Antonio
    Koltun, Vladlen
    Dosovitskiy, Alexey
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 4693 - 4700
  • [34] A Reference Resource Based End-to-End Image Compression Scheme
    Yin, Wenbin
    Fan, Xiaopeng
    Shi, Yunhui
    Zuo, Wangmeng
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING, PT I, 2018, 11164 : 534 - 544
  • [35] An End-to-End Image Dehazing Method Based on Deep Learning
    Zhang, Yi
    Huang, Hongbing
    Liu, Junyi
    Fan, Chao
    Wang, Yanyan
    Cai, Qing
    Ruan, Yingying
    Gong, Xiaojin
    2018 3RD INTERNATIONAL CONFERENCE ON COMMUNICATION, IMAGE AND SIGNAL PROCESSING, 2019, 1169
  • [36] End-to-end image quality assessment
    Raventos, Joaquin
    VISUAL INFORMATION PROCESSING XXI, 2012, 8399
  • [37] Encipher GAN: An End-to-End Color Image Encryption System Using a Deep Generative Model
    Panwar, Kirtee
    Singh, Akansha
    Kukreja, Sonal
    Singh, Krishna Kant
    Shakhovska, Nataliya
    Boichuk, Andrii
    SYSTEMS, 2023, 11 (01):
  • [38] Assessing Knee OA Severity with CNN attention-based end-to-end architectures
    Gorriz, Marc
    Antony, Joseph
    McGuinness, Kevin
    Giro-i-Nieto, Xavier
    O'Connor, Noel E.
    INTERNATIONAL CONFERENCE ON MEDICAL IMAGING WITH DEEP LEARNING, VOL 102, 2019, 102 : 197 - 214
  • [39] SCALABLE NEURAL ARCHITECTURES FOR END-TO-END ENVIRONMENTAL SOUND CLASSIFICATION
    Paissan, Francesco
    Ancilotto, Alberto
    Brutti, Alessio
    Farella, Elisabetta
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 641 - 645
  • [40] An End-to-End Security Auditing Approach for Service Oriented Architectures
    Azarmi, Mehdi
    Bhargava, Bharat
    Angin, Pelin
    Ranchal, Rohit
    Ahmed, Norman
    Sinclair, Asher
    Linderman, Mark
    Ben Othmane, Lotfi
    2012 31ST INTERNATIONAL SYMPOSIUM ON RELIABLE DISTRIBUTED SYSTEMS (SRDS 2012), 2012, : 279 - 284