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
  • [1] GAN-based End-to-End Unsupervised Image Registration for RGB-Infrared Image
    Kumari, Kanti
    Krishnamurthi, Ganapathy
    2020 THE 3RD INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS'2020), 2020, : 62 - 66
  • [2] A New GAN-based End-to-End TTS Training Algorithm
    Guo, Haohan
    Soong, Frank K.
    He, Lei
    Xie, Lei
    INTERSPEECH 2019, 2019, : 1288 - 1292
  • [3] MedViTGAN: End-to-End Conditional GAN for Histopathology Image Augmentation with Vision Transformers
    Li, Meng
    Li, Chaoyi
    Hobson, Peter
    Jennings, Tony
    Lovell, Brian C.
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 4406 - 4413
  • [4] Channel Agnostic End-to-End Learning based Communication Systems with Conditional GAN
    Ye, Hao
    Li, Geoffrey Ye
    Juang, Biing-Hwang Fred
    Sivanesan, Kathiravetpillai
    2018 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2018,
  • [5] End-to-End Unpaired Image Denoising with Conditional Adversarial Networks
    Hong, Zhiwei
    Fan, Xiaocheng
    Jiang, Tao
    Feng, Jianxing
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 4140 - 4149
  • [6] CLASS-CONDITIONAL DEFENSE GAN AGAINST END-TO-END SPEECH ATTACKS
    Esmaeilpour, Mohammad
    Cardinal, Patrick
    Koerich, Alessandro Lameiras
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 2565 - 2569
  • [7] Perceptual Conditional Generative Adversarial Networks for End-to-End Image Colourization
    Halder, Shirsendu Sukanta
    De, Kanjar
    Roy, Partha Pratim
    COMPUTER VISION - ACCV 2018, PT II, 2019, 11362 : 269 - 283
  • [8] CANDY: Conditional Adversarial Networks based End-to-End System for Single Image Haze Removal
    Swami, Kunal
    Das, Saikat Kumar
    2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 3061 - 3067
  • [9] End-to-end diagnostics in IPTV architectures
    Sridhar, Kamakshi
    Damm, Gerard
    Cankaya, Hakki C.
    BELL LABS TECHNICAL JOURNAL, 2008, 13 (01) : 29 - 34
  • [10] End-to-end Conditional Robust Optimization
    Chenreddy, Abhilash Reddy
    Delage, Erick
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2024, 244 : 736 - 748