Abstract
At present, sketch heads generated from realistic heads still has problems such as blurred contours and missing textures. For this reason, this work proposes a sketch head generation method based on CycleGAN. Firstly, the Self-Attention Mechanism (Squeeze-and-Excitation Networks (SENet) module is added to the UNet self-encoder; secondly, the base model is transformed into a supervised learning model so as to add constraints on the generated avatars and the real avatars. The experimental results show that the sketched avatar generated by the method in this paper has a better visual effect on the CUHK student test set with a 0.0274 improvement in SSIM value than the sketched avatar generated by the base model.
Publisher
Darcy & Roy Press Co. Ltd.
Reference17 articles.
1. Zhang S, Gao X, Wang N, et al. Face sketch synthesis via sparse representation-based greedy search [J]. IEEE transactions on image processing, 2015, 24(8): 2466-2477.
2. Chang L, Zhou M, Deng X, et al. Face sketch synthesis via multivariate output regression [C] // Human-Computer Interaction. Design and Development Approaches: 14th International Conference, HCI International 2011, Orlando, FL, USA, July 9-14, 2011, Proceedings, Part I 14. Springer Berlin Heidelberg, 2011: 555-561.
3. Wang X, Tang X. Face photo-sketch synthesis and recognition [J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 31(11): 1955-1967.
4. Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. science, 2000, 290(5500): 2323-2326.
5. Zhou H Q, Cao L, Du C N. Multi-discriminator recurrent generative adversarial network for sketch face synthesis[J]. Computer Engineering and Applications,2021,57(03):231-238.