Abstract
Cartoon pictures are a kind of art form that we often contact in our daily life, and generating different styles of cartoon pictures from a given real-life photo is a great promotion for the development of art. Aiming at the current existing methods in generating cartoon images appear in the degree of stylization is insufficient, the generalization ability of the situation is poor, this paper proposes a kind of improvement of the generation of adversarial network: in the generator module to join the adaptive normalization way to improve the generalization ability of the model; at the same time the introduction of the auxiliary discriminator to help the generator style to better present the different styles; in the data processing of this paper on the cartoon image to do guided filtering. The experimental results show that the cartoon image generated by the method of this paper is of higher quality and better effect.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.