ML Anthology

Layered Active Appearance Models

Eagle Jones, Stefano Soatto
ICCV 2005 pp. 1097-1102
doi:10.1109/ICCV.2005.133 /iccv/2005/jones2005iccv-layered/

Abstract

Active appearance models (AAMs) provide a framework for modeling the joint shape and texture of an image. An AAM is a compact representation of both factors in a conditionally linear model. However, the standard AAM framework does not handle images which have missing features, or allow modification of certain structures in the image while leaving neighboring ones undeformed. We introduce the layered active appearance model (LAAM), which allows for missing features, occlusion, substantial spatial rearrangement of features, and which provides a more general representation that extends the applicability of the active appearance model

ICCV Semantic Scholar

Cite

Text

Jones and Soatto. "Layered Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.133

Markdown

[Jones and Soatto. "Layered Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/jones2005iccv-layered/) doi:10.1109/ICCV.2005.133

BibTeX

@inproceedings{jones2005iccv-layered,
  title     = {{Layered Active Appearance Models}},
  author    = {Jones, Eagle and Soatto, Stefano},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1097-1102},
  doi       = {10.1109/ICCV.2005.133},
  url       = {https://mlanthology.org/iccv/2005/jones2005iccv-layered/}
}