An Improved Style Transfer Approach for Videos

檔案

本條目沒有附加檔案。

日期

2018-01-01

期刊名稱

2018 INTERNATIONAL WORKSHOP ON ADVANCED IMAGE TECHNOLOGY (IWAIT)

ISSN

2306-2274

語言

英文

摘要

In this paper, we present an improved approach to transfer style for videos based on semantic segmentation. We segment foreground objects and background, and then apply different styles respectively. A fully convolutional neural network is used to perform semantic segmentation. We increase the reliability of the segmentation, and use the information of segmentation and the relationship between foreground objects and background to improve segmentation iteratively. We also use segmentation to improve optical flow, and apply different motion estimation methods between foreground objects and background. This improves the motion boundaries of optical flow, and solves the problems of incorrect and discontinuous segmentation caused by occlusion and shape deformation.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chang, R.-J., Chang, C.-C., Way, D.-L., & Shih, Z. C. (2018). An Improved Style Transfer Approach for Videos. 2018 INTERNATIONAL WORKSHOP ON ADVANCED IMAGE TECHNOLOGY (IWAIT). https://ir.lib.nycu.edu.tw/handle/11536/146200

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/146200