Multi-layered Expression Synthesis

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.