Loading...

Gray-scale image colorization using cycle-consistent generative adversarial networks with residual structure enhancer

Johari, M. M ; Sharif University of Technology | 2020

418 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ICASSP40776.2020.9054432
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2020
  4. Abstract:
  5. The colorization of gray-scale images has always been a challenging task in computer vision. Recently, novel approaches have been introduced for unsupervised image translation between two domains using Generative Adversarial Networks (GANs). Since one can consider the gray-scale and colorful images as two separate domains, we propose a two-stage cycle-consistent network architecture to produce convincible images. First, an intermediate image is generated with a relatively uncomplicated objective function at the output. Next, at the second stage, the intermediate image is enhanced via a residual network structure with a more complicated objective function. Furthermore, by employing two inverse networks, a cycle-consistent architecture is formed at both stages. The proposed model is trained on the ImageNet dataset, and the achieved outcomes demonstrate exceptional performance comparing with the state-of-the-art models. © 2020 IEEE
  6. Keywords:
  7. Cycle-Consistency ; Generative Adversarial Networks ; Image Colorization ; Residual Structure ; Audio signal processing ; Network architecture ; Speech communication ; Adversarial networks ; Gray-scale images ; Image translation ; Intermediate image ; Network structures ; Objective functions ; Residual structure ; State of the art ; Image enhancement
  8. Source: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, 4 May 2020 through 8 May 2020 ; Volume 2020 , May , 2020 , Pages 2223-2227
  9. URL: https://ieeexplore.ieee.org/document/9054432