2020
DOI: 10.1007/s10489-020-01931-w
|View full text |Cite
|
Sign up to set email alerts
|

Local-CycleGAN: a general end-to-end network for visual enhancement in complex deep-water environment

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
10
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 28 publications
(12 citation statements)
references
References 19 publications
0
10
0
Order By: Relevance
“…Judging by the students' assessment of whether the concept of content management and whether the management meets the needs of the Internet age, 31.39% of students answered that “control,” and 19.71% and 16.42% of students considered “change” and “adapt,” respectively (see Figure 16 ). It seems that how to change the concept and management system to meet the needs of the network age has become an important issue that needs to be addressed [ 25 ].…”
Section: Current Status and Issues Of College Students' Ideological A...mentioning
confidence: 99%
“…Judging by the students' assessment of whether the concept of content management and whether the management meets the needs of the Internet age, 31.39% of students answered that “control,” and 19.71% and 16.42% of students considered “change” and “adapt,” respectively (see Figure 16 ). It seems that how to change the concept and management system to meet the needs of the network age has become an important issue that needs to be addressed [ 25 ].…”
Section: Current Status and Issues Of College Students' Ideological A...mentioning
confidence: 99%
“…With continuous research by scholars in various fields, CycleGAN has gradually been widely used in the field of image data augmentation. [47,48] Using local and global discriminators, Zong et al [47] came up with a generative adversarial network that constrains both the global and local effects of images with a local cycle-consistent approach. Training of the network was controlled via a feedback mechanism to enhance deepwater images from complex environments.…”
Section: Data Augmentationmentioning
confidence: 99%
“…[ 47,48 ] Using local and global discriminators, Zong et al. [ 47 ] came up with a generative adversarial network that constrains both the global and local effects of images with a local cycle‐consistent approach. Training of the network was controlled via a feedback mechanism to enhance deepwater images from complex environments.…”
Section: Related Workmentioning
confidence: 99%
“…The network can learn a loss function to train the mapping from input images to output images. Zong et al [13] proposed a local cycle-consistent generative adversarial network to enhance images acquired in a complex deep-water environment. These methods assume that the image to be enhanced is of low resolution but cannot provide satisfactory results when applied to UHD images taken by DSLR cameras.…”
Section: Introductionmentioning
confidence: 99%