Name
Abstract | ||
|---|---|---|
In this paper, we present a novel geometry video (GV) framework to model and compress 3-D facial expressions. GV bridges the gap of 3-D motion data and 2-D video, and provides a natural way to apply the well-studied video processing techniques to motion data processing. Our framework includes a set of algorithms to construct GVs, such as hole filling, geodesic-based face segmentation, expression-invariant parameterization (EIP), and GV compression. Our EIP algorithm can guarantee the exact correspondence of the salient features (eyes, mouth, and nose) in different frames, which leads to GVs with better spatial and temporal coherence than that of the conventional parameterization methods. By taking advantage of this feature, we also propose a new H.264/AVC-based progressive directional prediction scheme, which can provide further 10%–16% bitrate reductions compared to the original H.264/AVC applied for GV compression while maintaining good video quality. Our experimental results on real-world datasets demonstrate that GV is very effective for modeling the high-resolution 3-D expression data, thus providing an attractive way in expression information processing for gaming and movie industry. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TCSVT.2011.2158337 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
expression information processing,2-d video,compress 3-d facial expression,novel geometry video,geometry videos,good video quality,gv compression,3-d facial,high-resolution 3-d expression data,well-studied video processing technique,gv bridge,3-d motion data,video compression,information processing,facial expression,video quality,three dimensional,face,data processing,video processing,face recognition,high resolution,data compression,geometry | Data processing,Computer science,Artificial intelligence,Geometry,Video quality,Computer vision,Facial recognition system,Video processing,Pattern recognition,Segmentation,Facial expression,Data compression,Geodesic | Journal |
Volume | Issue | ISSN |
22 | 1 | 1051-8215 |
Citations | PageRank | References |
12 | 0.56 | 33 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jiazhi Xia | 1 | 204 | 17.04 |
| Dao Thi Phuong Quynh | 2 | 21 | 1.18 |
| Ying He | 3 | 1264 | 105.35 |
| Xiaoming Chen | 4 | 50 | 4.50 |
| Steven C. H. Hoi | 5 | 3830 | 174.61 |