Joint sparse learning for 3-D facial expression generation

Publication Type:
Journal Article
IEEE Transactions On Image Processing, 2013, 22 (8), pp. 3283 - 3295
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2012006165OK.pdf1.73 MB
Adobe PDF
3-D facial expression generation, including synthesis and retargeting, has received intensive attentions in recent years, because it is important to produce realistic 3-D faces with speci?c expressions in modern ?lm production and computer games. In this paper, we present joint sparse learning (JSL) to learn mapping functions and their respective inverses to model the relationship between the high-dimensional 3-D faces (of different expressions and identities) and their corresponding low-dimensional representations. Based on JSL, we can effectively and ef?ciently generate various expressions of a 3-D face by either synthesizing or retargeting. Furthermore, JSL is able to restore 3-D faces with holes by learning a mapping function between incomplete and intact data. Experimental results on a wide range of 3-D faces demonstrate the effectiveness of the proposed approach by comparing with representative ones in terms of quality, time cost, and robustness.
Please use this identifier to cite or link to this item: