Learning to Create Cartoon Images from a Very Small Dataset

Hsu Yung Cheng, Chih Chang Yu

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

This paper proposes a framework to automatically create cartoon images with low computation resources and small training datasets. The system segments and reassembles regions according to the topologies learned from example images. Region relationship trees are constructed for training images with no requirement of manual labeling. An enhanced clustering mechanism with no prior knowledge of cluster number is designed to effectively group components into desired groups for image creation. Compared with methods based on Generative Adversarial Networks, the proposed framework which performs automatic reasoning, clustering and reassembling regions of cartoon images can create better images with a very small amount of training samples.

原文???core.languages.en_GB???
主出版物標題2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
發行者IEEE Computer Society
頁面4684-4688
頁數5
ISBN(電子)9781538662496
DOIs
出版狀態已出版 - 9月 2019
事件26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan
持續時間: 22 9月 201925 9月 2019

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
2019-September
ISSN(列印)1522-4880

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???26th IEEE International Conference on Image Processing, ICIP 2019
國家/地區Taiwan
城市Taipei
期間22/09/1925/09/19

指紋

深入研究「Learning to Create Cartoon Images from a Very Small Dataset」主題。共同形成了獨特的指紋。

引用此