COMPONENT-BASED TRANSFORMATION FOR PERSON IMAGE GENERATION

Wen Jiin Tsai, Po Hsiang Chen

研究成果: Conference contribution同行評審

摘要

Person image generation has attracted more and more attention because it has many applications. This paper focuses on pose transfer and virtual try-on. We propose a flow-based method called attribute-decomposited spatial transformation network. It warps different body parts separately using segmentation and then fuses different body parts and generates images. The flow-based technique enables the model to generate high-quality person images for pose transfer and the attribute-decomposited technique enables the model to support virtual try-on. The proposed method was evaluated on Deepfashion dataset. Quantitative and qualitative experimental results show the superiority of the method.

原文English
主出版物標題2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
發行者IEEE Computer Society
頁面4108-4112
頁數5
ISBN(電子)9781665496209
DOIs
出版狀態Published - 2022
事件29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
持續時間: 16 10月 202219 10月 2022

出版系列

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

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
國家/地區France
城市Bordeaux
期間16/10/2219/10/22

指紋

深入研究「COMPONENT-BASED TRANSFORMATION FOR PERSON IMAGE GENERATION」主題。共同形成了獨特的指紋。

引用此