ML Anthology

Out-of-Core Surface Reconstruction via Global TGV Minimization

Nikolai Poliarnyi
ICCV 2021 pp. 5641-5650
doi:10.1109/ICCV48922.2021.00559 /iccv/2021/poliarnyi2021iccv-outofcore/

Abstract

We present an out-of-core variational approach for surface reconstruction from a set of aligned depth maps. Input depth maps are supposed to be reconstructed from regular photos or/and can be a representation of terrestrial LIDAR point clouds. Our approach is based on surface reconstruction via total generalized variation minimization (TGV) because of its strong visibility-based noise-filtering properties and GPU-friendliness. Our main contribution is an out-of-core OpenCL-accelerated adaptation of this numerical algorithm which can handle arbitrarily large real-world scenes with scale diversity.

PDF ICCV Semantic Scholar

Cite

Text

Poliarnyi. "Out-of-Core Surface Reconstruction via Global TGV Minimization." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00559

Markdown

[Poliarnyi. "Out-of-Core Surface Reconstruction via Global TGV Minimization." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/poliarnyi2021iccv-outofcore/) doi:10.1109/ICCV48922.2021.00559

BibTeX

@inproceedings{poliarnyi2021iccv-outofcore,
  title     = {{Out-of-Core Surface Reconstruction via Global TGV Minimization}},
  author    = {Poliarnyi, Nikolai},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {5641-5650},
  doi       = {10.1109/ICCV48922.2021.00559},
  url       = {https://mlanthology.org/iccv/2021/poliarnyi2021iccv-outofcore/}
}