- Tytuł:
- Underwater image enhancement via efficient generative adversarial network
- Autorzy:
-
Qian, Xin
Ge, Peng - Powiązania:
- https://bibliotekanauki.pl/articles/2033886.pdf
- Data publikacji:
- 2021
- Wydawca:
- Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
- Tematy:
-
underwater
image dehazing
generative adversarial network
GAN - Opis:
- Underwater image enhancement has been receiving much attention due to its significance in facilitating various marine explorations. Inspired by the generative adversarial network (GAN) and residual network (ResNet) in many vision tasks, we propose a simplified designed ResNet model based on GAN called efficient GAN (EGAN) for underwater image enhancement. In particular, for the generator of EGAN we design a new pair of convolutional kernel size for the residual block in the ResNet. Secondly, we abandon batch normalization (BN) after every convolution layer for faster training and less artifacts. Finally, a smooth loss function is introduced for halo-effect alleviation. Extensive qualitative and quantitative experiments show that our methods accomplish considerable improvements compared to the state-of-the-art methods.
- Źródło:
-
Optica Applicata; 2021, 51, 4; 483-497
0078-5466
1899-7015 - Pojawia się w:
- Optica Applicata
- Dostawca treści:
- Biblioteka Nauki
Artykuł