Deformable Model-Based Shape and Motion Analysis from Images Using Motion Residual Error

Abstract

We present a novel method for the shape and motion estimation of a deformable model using error residuals from model-based motion analysis. The motion of the model is first estimated using a model-based least squares method. Using the residuals from the least squares solution, the non-rigid structure of the model can be better estimated by computing how changes in the shape of the model affect its motion parameterization. This method is implemented as a component in a deformable model-based framework that uses optical flow information and edges. This general model-based framework is applied to human face shape and motion estimation. We present experiments that demonstrate that this framework is a considerable improvement over a framework that uses only optical flow information and edges.

Cite

Text

DeCarlo and Metaxas. "Deformable Model-Based Shape and Motion Analysis from Images Using Motion Residual Error." IEEE/CVF International Conference on Computer Vision, 1998. doi:10.1109/ICCV.1998.710708

Markdown

[DeCarlo and Metaxas. "Deformable Model-Based Shape and Motion Analysis from Images Using Motion Residual Error." IEEE/CVF International Conference on Computer Vision, 1998.](https://mlanthology.org/iccv/1998/decarlo1998iccv-deformable/) doi:10.1109/ICCV.1998.710708

BibTeX

@inproceedings{decarlo1998iccv-deformable,
  title     = {{Deformable Model-Based Shape and Motion Analysis from Images Using Motion Residual Error}},
  author    = {DeCarlo, Douglas and Metaxas, Dimitris N.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1998},
  pages     = {113-119},
  doi       = {10.1109/ICCV.1998.710708},
  url       = {https://mlanthology.org/iccv/1998/decarlo1998iccv-deformable/}
}