High-Detail 3D Capture and Non-sequential Alignment of Facial Performance

  title={High-Detail 3D Capture and Non-sequential Alignment of Facial Performance},
  author={Martin Klaudiny and Adrian Hilton},
  journal={2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission},
This paper presents a novel system for the 3D capture of facial performance using standard video and lighting equipment. The mesh of an actor's face is tracked non-sequentially throughout a performance using multi-view image sequences. The minimum spanning tree calculated in expression dissimilarity space defines the traversal of the sequences optimal with respect to error accumulation. A robust patch-based frame-to-frame surface alignment combined with the optimal traversal significantly… CONTINUE READING
Highly Cited
This paper has 42 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 27 extracted citations


Publications referenced by this paper.
Showing 1-10 of 24 references

Dense 3D motion capture for human faces

2009 IEEE Conference on Computer Vision and Pattern Recognition • 2009
View 8 Excerpts
Highly Influenced

High-quality passive facial performance capture using anchor frames

SIGGRAPH '11 • 2011
View 6 Excerpts
Highly Influenced

Self-calibrated, Multi-spectral Photometric Stereo for 3D Face Capture

International Journal of Computer Vision • 2011
View 4 Excerpts
Highly Influenced

High-detail 3d capture of facial performance

M. Klaudiny, A. Hilton, J. Edge
3DPVT, 2010. • 2010
View 5 Excerpts
Highly Influenced

Cooperative patch-based 3D surface tracking

2011 Conference for Visual Media Production • 2011
View 3 Excerpts

Similar Papers

Loading similar papers…