TY - GEN
T1 - Advancing Comic Image Inpainting
T2 - 31st International Conference on Neural Information Processing, ICONIP 2024
AU - Hong, Zilan
AU - Cheng, Lianglun
AU - Huang, Guoheng
AU - Chen, Xuhang
AU - Pun, Chi Man
AU - Yuan, Xiaochen
AU - Zhong, Guo
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - In the process of comic localization, a crucial step is to fill in the pixels obscured due to the removal of dialogue boxes or sound effect text. Comic inpainting is more challenging than natural images. On one hand, its structure and texture are highly abstract, which confuses semantic interpretation and content synthesis. On the other hand, high-frequency information specific to comic images (such as lines and dots) is crucial for visual representation. This paper proposes the Texture-Structure Fusion Network (TSF-Net) with dual-stream encoder, introducing the Dual-stream Space-Gated Fusion (DSSGF) module for effective feature interaction. Additionally, a Multi-scale Histogram Texture Enhancement (MHTE) module is designed to enhance texture information aggregation dynamically. Visual comparisons and quantitative experiments demonstrate the effectiveness of the method, proving its superiority over existing techniques in comic inpainting. The implementation methods and dataset can be obtained from https://github.com/arashi-knight/comic-inpaint-pre.
AB - In the process of comic localization, a crucial step is to fill in the pixels obscured due to the removal of dialogue boxes or sound effect text. Comic inpainting is more challenging than natural images. On one hand, its structure and texture are highly abstract, which confuses semantic interpretation and content synthesis. On the other hand, high-frequency information specific to comic images (such as lines and dots) is crucial for visual representation. This paper proposes the Texture-Structure Fusion Network (TSF-Net) with dual-stream encoder, introducing the Dual-stream Space-Gated Fusion (DSSGF) module for effective feature interaction. Additionally, a Multi-scale Histogram Texture Enhancement (MHTE) module is designed to enhance texture information aggregation dynamically. Visual comparisons and quantitative experiments demonstrate the effectiveness of the method, proving its superiority over existing techniques in comic inpainting. The implementation methods and dataset can be obtained from https://github.com/arashi-knight/comic-inpaint-pre.
KW - Comic image inpainting
KW - Deep neural network
KW - Dual-stream fusion
UR - https://www.scopus.com/pages/publications/105009896915
U2 - 10.1007/978-981-96-6969-1_13
DO - 10.1007/978-981-96-6969-1_13
M3 - Conference contribution
AN - SCOPUS:105009896915
SN - 9789819669684
T3 - Communications in Computer and Information Science
SP - 181
EP - 195
BT - Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings
A2 - Mahmud, Mufti
A2 - Doborjeh, Maryam
A2 - Wong, Kevin
A2 - Leung, Andrew Chi Sing
A2 - Doborjeh, Zohreh
A2 - Tanveer, M.
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 2 December 2024 through 6 December 2024
ER -