Multi-layered expression synthesis

Jia Ru Lin*, I-Chen Lin

*Corresponding author for this work

Research output: Contribution to journalArticle

1 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)337-351
Number of pages15
JournalJournal of Information Science and Engineering
Volume27
Issue number1
StatePublished - 1 Jan 2011

Keywords

  • Blend shape
  • Detail preservation
  • Facial expression
  • Image editing
  • Steerable pyramid

Fingerprint Dive into the research topics of 'Multi-layered expression synthesis'. Together they form a unique fingerprint.

  • Cite this