TY - GEN
T1 - Weather Attribute-Aware Multi-Scale Image Generation with Residual Learning
AU - Chu, Wei Ta
AU - Huang, Li Wei
N1 - Funding Information:
ACKNOWLEDGMENT This work was partially supported by the Ministry of Science and Technology, Taiwan, under the grant 108-2221-E-006-227-MY3, 107-2221-E-006-239-MY2, 107-2923-E-194-003-MY3, 107-2627-H-155-001, and 107-2218-E-002-055.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - We present image generation networks to generate images conforming to specified weather attributes. Taking weather attributes as the conditions, the proposed networks generate scene images with the help of a guided reference image. To generate higher-resolution images, we construct a multi-scale generation framework consisting of a global generator and a local enhancer. Furthermore, we integrate the idea of residual learning into the proposed framework, and aim at generating fine-grained texture. The evaluation shows performance comparison both from quantitative and qualitative perspectives. A comprehensive study including the impact of different attributes and extension of the proposed models is also provided. This work is kind of hybrid approach among various image generation studies.
AB - We present image generation networks to generate images conforming to specified weather attributes. Taking weather attributes as the conditions, the proposed networks generate scene images with the help of a guided reference image. To generate higher-resolution images, we construct a multi-scale generation framework consisting of a global generator and a local enhancer. Furthermore, we integrate the idea of residual learning into the proposed framework, and aim at generating fine-grained texture. The evaluation shows performance comparison both from quantitative and qualitative perspectives. A comprehensive study including the impact of different attributes and extension of the proposed models is also provided. This work is kind of hybrid approach among various image generation studies.
UR - http://www.scopus.com/inward/record.url?scp=85092147085&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092147085&partnerID=8YFLogxK
U2 - 10.1109/Indo-TaiwanICAN48429.2020.9181357
DO - 10.1109/Indo-TaiwanICAN48429.2020.9181357
M3 - Conference contribution
AN - SCOPUS:85092147085
T3 - Indo - Taiwan 2nd International Conference on Computing, Analytics and Networks, Indo-Taiwan ICAN 2020 - Proceedings
SP - 238
EP - 243
BT - Indo - Taiwan 2nd International Conference on Computing, Analytics and Networks, Indo-Taiwan ICAN 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - Indo - Taiwan 2nd International Conference on Computing, Analytics and Networks, Indo-Taiwan ICAN 2020
Y2 - 7 February 2020 through 15 February 2020
ER -