Component-Wise Modeling of Articulated Objects

Abstract

We introduce a novel framework for modeling articulated objects based on the aspects of their components. By decomposing the object into components, we divide the problem in smaller modeling tasks. After obtaining 3D models for each component aspect by employing a shape deformation paradigm, we merge them together, forming the object components. The final model is obtained by assembling the components using an optimization scheme which fits the respective 3D models to the corresponding apparent contours in a reference pose. The results suggest that our approach can produce realistic 3D models of articulated objects in reasonable time.

Cite

Text

Ntouskos et al. "Component-Wise Modeling of Articulated Objects." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.268

Markdown

[Ntouskos et al. "Component-Wise Modeling of Articulated Objects." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/ntouskos2015iccv-componentwise/) doi:10.1109/ICCV.2015.268

BibTeX

@inproceedings{ntouskos2015iccv-componentwise,
  title     = {{Component-Wise Modeling of Articulated Objects}},
  author    = {Ntouskos, Valsamis and Sanzari, Marta and Cafaro, Bruno and Nardi, Federico and Natola, Fabrizio and Pirri, Fiora and Ruiz, Manuel},
  booktitle = {International Conference on Computer Vision},
  year      = {2015},
  doi       = {10.1109/ICCV.2015.268},
  url       = {https://mlanthology.org/iccv/2015/ntouskos2015iccv-componentwise/}
}