English

Guided Depth Upsampling for Precise Mapping of Urban Environments

Computational Geometry 2017-06-20 v1

Abstract

We present an improved model for MRF-based depth upsampling, guided by image- as well as 3D surface normal features. By exploiting the underlying camera model we define a novel regularization term that implicitly evaluates the planarity of arbitrary oriented surfaces. Our method improves upsampling quality in scenes composed of predominantly planar surfaces, such as urban areas. We use a synthetic dataset to demonstrate that our approach outperforms recent methods that implement distance-based regularization terms. Finally, we validate our approach for mapping applications on our experimental vehicle.

Keywords

Cite

@article{arxiv.1706.05999,
  title  = {Guided Depth Upsampling for Precise Mapping of Urban Environments},
  author = {Sascha Wirges and Björn Roxin and Eike Rehder and Tilman Kühner and Martin Lauer},
  journal= {arXiv preprint arXiv:1706.05999},
  year   = {2017}
}

Comments

6 pages, 6 figures

R2 v1 2026-06-22T20:22:48.992Z