標題: Multi-layered Expression Synthesis
作者: Lin, Jia-Ru
Lin, I-Chen
多媒體工程研究所
Institute of Multimedia Engineering
關鍵字: facial expression;blend shape;image editing;steerable pyramid;detail preservation
公開日期: 1-Jan-2011
摘要: In this paper, a feature-point-driven expression editing and synthesis framework is proposed. While the extensively used blend shape methods suffer detail losing during image blending, the proposed multi-layer method can retain the flexibility and variety of geometry editing and preserve detail features as well. For low-frequency sub-bands, optimization-based blend shape is presented for large-to-mid scale synthesis. In addition, statistics-based feature matching and enhancement are proposed for high-frequency details. Our results show that the proposed methods are adequate to high-resolution expression synthesis and detail-preserved image editing.
URI: http://hdl.handle.net/11536/26157
ISSN: 1016-2364
期刊: JOURNAL OF INFORMATION SCIENCE AND ENGINEERING
Volume: 27
Issue: 1
起始頁: 337
結束頁: 351
Appears in Collections:Articles


Files in This Item:

  1. 000286692500022.pdf