G2L-CariGAN: Caricature Generation from Global Structure to Local Features
Xin Huang, Yunfeng Bai, Dong Liang, Feng Tian, Jinyuan Jia
Abstract
Existing GAN-based approaches to caricature generation mainly focus on exaggerating a character’s global facial structure. This often leads to the failure in highlighting significant facial features such as big eyes and hook nose. To address this limitation, we propose a new approach termed as G2L-CariGAN, which uses feature maps of spatial dimensions instead of latent codes for geometric exaggeration. G2L-CariGAN first exaggerates the global facial structure of the character on a low-dimensional feature map and then exaggerates its local facial features on a high-dimensional feature map. Moreover, we develop a caricature identity loss function based on feature maps, which well retains the character's identity after exaggeration. Our experiments have demonstrated that G2L-CariGAN outperforms the state-of-arts in terms of the quality of exaggerating a character and retaining its identity.
BibTeX
@article{Huang_Bai_Liang_Tian_Jia_2024, title={G2L-CariGAN: Caricature Generation from Global Structure to Local Features}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/28014}, DOI={10.1609/aaai.v38i3.28014}, abstractNote={Existing GAN-based approaches to caricature generation mainly focus on exaggerating a character’s global facial structure. This often leads to the failure in highlighting significant facial features such as big eyes and hook nose. To address this limitation, we propose a new approach termed as G2L-CariGAN, which uses feature maps of spatial dimensions instead of latent codes for geometric exaggeration. G2L-CariGAN first exaggerates the global facial structure of the character on a low-dimensional feature map and then exaggerates its local facial features on a high-dimensional feature map. Moreover, we develop a caricature identity loss function based on feature maps, which well retains the character’s identity after exaggeration. Our experiments have demonstrated that G2L-CariGAN outperforms the state-of-arts in terms of the quality of exaggerating a character and retaining its identity.}, number={3}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Huang, Xin and Bai, Yunfeng and Liang, Dong and Tian, Feng and Jia, Jinyuan}, year={2024}, month={Mar.}, pages={2391-2399} }