@inproceedings{51a7c4abf4314ed2a03b714f4c2df293,
title = "Intrinsic Morphological Relationship Guided 3D Craniofacial Reconstruction Using Siamese Cycle Attention GAN",
abstract = "Craniofacial reconstruction is essential in forensic science and has widespread applications. It is challenging due to the detailed facial geometry, complex skull topology, and nonlinear skull-face relationship. We propose a novel approach for 3D craniofacial reconstruction using a Siamese cycle attention mechanism within Generative Adversarial Networks (GAN). Benefiting from the cycle attention mechanism, our method focuses on high-frequency features and morphological connections between the skull and face. Additionally, a Siamese network preserves its identity consistently. Extensive experiments demonstrate superior accuracy and high-quality details of our approach.",
keywords = "Craniofacial reconstruction, Cycle Attention GAN, Intrinsic morphological relationship, Siamese network",
author = "Junli Zhao and Chengyuan Wang and Wen, \{Yu Hui\} and Fuqing Duan and Ran Yi and Liu, \{Yong Jin\} and Qingdong Long and Zhenkuan Pan and Xianfeng Gu",
note = "Publisher Copyright: {\textcopyright} 2024 Copyright held by the owner/author(s).; 2024 SIGGRAPH Asia 2024 Technical Communications, SA 2024 ; Conference date: 03-12-2024 Through 06-12-2024",
year = "2024",
month = dec,
day = "3",
doi = "10.1145/3681758.3698016",
language = "English",
series = "Proceedings - SIGGRAPH Asia 2024 Technical Communications, SA 2024",
publisher = "Association for Computing Machinery, Inc",
editor = "Spencer, \{Stephen N.\}",
booktitle = "Proceedings - SIGGRAPH Asia 2024 Technical Communications, SA 2024",
}