Morphable 3D models from video
- 25 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10636919)
- https://doi.org/10.1109/cvpr.2001.990997
Abstract
Nonrigid 3D structure-from-motion and 2D optical flow can both be formulated as tensor factorization problems. The two problems can be made equivalent through a noisy affine transform, yielding a combined nonrigid structure-from-intensities problem that we solve via structured matrix decompositions. Often the preconditions for this factorization are violated by image noise and deficiencies of the data visa-vis the sample complexity of the problem. Both issues are remediated with careful use of rank constraints, norm constraints, and integration over uncertainty in the intensity values, yielding novel solutions for SVD under uncertainty, factorization under uncertainty, nonrigid factorization, and subspace optical flow. The resulting integrated algorithm can track and reconstruct in 3D nonrigid surfaces having very little texture, for example the smooth parts of the face. Working with low-resolution low-texture "found video," these methods produce good tracking and 3D reconstruction results where prior algorithms fail.Keywords
This publication has 5 references indexed in Scilit:
- Flexible flow for 3D nonrigid tracking and shape recoveryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Recovering non-rigid 3D shape from image streamsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A morphable model for the synthesis of 3D facesPublished by Association for Computing Machinery (ACM) ,1999
- Multi-frame optical flow estimation using subspace constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992