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_24Markdown
[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_24BibTeX
@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/}
}