Automatic Non-Rigid 3D Modeling from Video

Abstract

We present a robust framework for estimating non-rigid 3D shape and motion in video sequences. Given an input video sequence, and a user-specified region to reconstruct, the algorithm automatically solves for the 3D time-varying shape and motion of the object, and estimates which pixels are outliers, while learning all system parameters, including a PDF over non-rigid deformations. There are no user-tuned parameters (other than initialization); all parameters are learned by maximizing the likelihood of the entire image stream. We apply our method to both rigid and non-rigid shape reconstruction, and demonstrate it in challenging cases of occlusion and variable illumination.

Cite

Text

Torresani and Hertzmann. "Automatic Non-Rigid 3D Modeling from Video." European Conference on Computer Vision, 2004. doi:10.1007/978-3-540-24671-8_24

Markdown

[Torresani and Hertzmann. "Automatic Non-Rigid 3D Modeling from Video." European Conference on Computer Vision, 2004.](https://mlanthology.org/eccv/2004/torresani2004eccv-automatic/) doi:10.1007/978-3-540-24671-8_24

BibTeX

@inproceedings{torresani2004eccv-automatic,
  title     = {{Automatic Non-Rigid 3D Modeling from Video}},
  author    = {Torresani, Lorenzo and Hertzmann, Aaron},
  booktitle = {European Conference on Computer Vision},
  year      = {2004},
  pages     = {299-312},
  doi       = {10.1007/978-3-540-24671-8_24},
  url       = {https://mlanthology.org/eccv/2004/torresani2004eccv-automatic/}
}