NRST: Non-rigid Surface Tracking from Monocular Video

German Conference on Pattern Recognition(2018), Stuttgart, Germany

Download Video: HD (MP4, 41 MB)

Abstract

We propose an efficient method for non-rigid surface tracking from monocular RGB videos. Given a video and a template mesh, our algorithm sequentially registers the template non-rigidly to each frame.We formulate the per-frame registration as an optimization problem that includes a novel texture term specifically tailored towards tracking objects with uniform texture but fine-scale structure, such as the regular micro-structural patterns of fabric. Our texture term exploits the orientation information in the micro-structures of the objects, e.g., the yarn patterns of fabrics. This enables us to accurately track uniformly colored materials that have these high frequency micro-structures, for which traditional photometric terms are usually less effective. The results demonstrate the effectiveness of our method on both general textured non-rigid objects and monochromatic fabrics.

Downloads


Citation

BibTeX, 1 KB

@inproceedings{NRST_GCPR2018,
 author = {Habermann, Marc and Xu, Weipeng and Rhodin, Helge and Zollhoefer, Michael and Pons-Moll, Gerard and Theobalt, Christian},
 title = {NRST: Non-rigid Surface Tracking from Monocular Video},
 booktitle = {Proceedings of German Conference on Pattern Recognition ({GCPR})},
 url = {https://people.mpi-inf.mpg.de/~mhaberma/projects/2018-gcpr-nrst/},
 numpages = {TODO},
 month = {TODO},
 year = {2018}
}
		

Acknowledgments

This work is funded by the ERC Starting Grant project CapReal (335545).

Contact

For questions, clarifications, please get in touch with:
Marc Habermann
mhaberma@mpi-inf.mpg.de

This page is Zotero translator friendly. Page last updated .Imprint. Data Protection.