TY - GEN
T1 - A Multi-Feature Migration Fog Generation Model
AU - Ai, Xin
AU - Zhang, Jia
AU - Bai, Yongqiang
AU - Song, Hongxing
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The dehaze methods are limited because authenticity of the synthesized dataset has not yet met the requirements for dehazing in real-world scenarios. The traditional image domain migration methods exhibit an uneven problem in fog generation. We propose a characteristic transfer fog generative model (FogGAN) for the synthesis of haze datasets. Firstly, we propose a multi-feature fusion strategy for haze distribution based on the principle of atmospheric scattering. We use transmission maps, depth maps, and mask maps to obtain the distribution of haze and transfer the fused information to the source domain. Secondly, in order to improve the error fitting phenomenon of multicommon information in the target domain, we designed a multi-layer attention module (MAConv). It focuses the neural network on the features of fog and excludes interference from other content. To address the issue of missing details in generated images. We conducted experiments on the VOC2007 dataset. It demonstrates the effectiveness and the ability to improve existing dehaze methods.
AB - The dehaze methods are limited because authenticity of the synthesized dataset has not yet met the requirements for dehazing in real-world scenarios. The traditional image domain migration methods exhibit an uneven problem in fog generation. We propose a characteristic transfer fog generative model (FogGAN) for the synthesis of haze datasets. Firstly, we propose a multi-feature fusion strategy for haze distribution based on the principle of atmospheric scattering. We use transmission maps, depth maps, and mask maps to obtain the distribution of haze and transfer the fused information to the source domain. Secondly, in order to improve the error fitting phenomenon of multicommon information in the target domain, we designed a multi-layer attention module (MAConv). It focuses the neural network on the features of fog and excludes interference from other content. To address the issue of missing details in generated images. We conducted experiments on the VOC2007 dataset. It demonstrates the effectiveness and the ability to improve existing dehaze methods.
KW - dehaze methods
KW - domain adaptation
KW - generate hazy images
KW - multi-feature fusion
KW - multicommon information
UR - https://www.scopus.com/pages/publications/85203788286
U2 - 10.1109/ICRCA60878.2024.10649102
DO - 10.1109/ICRCA60878.2024.10649102
M3 - Conference contribution
AN - SCOPUS:85203788286
T3 - 2024 8th International Conference on Robotics, Control and Automation, ICRCA 2024
SP - 248
EP - 252
BT - 2024 8th International Conference on Robotics, Control and Automation, ICRCA 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th International Conference on Robotics, Control and Automation, ICRCA 2024
Y2 - 12 January 2024 through 14 January 2024
ER -