Joint Estimation of Depth, Reflectance and Illumination for Depth Refinement

Abstract

In this paper we propose a method for joint estimation of depth, reflectance and illumination from a single RGB-D image for depth refinement. This is achieved by a simple optimization based approach with smoothness constraints on depth, reflectance and illumination. We introduce an adaptively weighted local similarity constraint for reflectance, a normalized spherical-harmonic model for illumination, and an edge-aware local smoothness constraint for depth. This allows us to generate high quality depth without additional processes such as pre-training of stochastic models or image segmentation. Experimental results demonstrate that our method estimates high quality depth in comparison with ground-truth data not only for laboratory conditions but also for complex real-world scenes.

Cite

Text

Kim et al. "Joint Estimation of Depth, Reflectance and Illumination for Depth Refinement." IEEE/CVF International Conference on Computer Vision Workshops, 2015. doi:10.1109/ICCVW.2015.35

Markdown

[Kim et al. "Joint Estimation of Depth, Reflectance and Illumination for Depth Refinement." IEEE/CVF International Conference on Computer Vision Workshops, 2015.](https://mlanthology.org/iccvw/2015/kim2015iccvw-joint/) doi:10.1109/ICCVW.2015.35

BibTeX

@inproceedings{kim2015iccvw-joint,
  title     = {{Joint Estimation of Depth, Reflectance and Illumination for Depth Refinement}},
  author    = {Kim, Kichang and Torii, Akihiko and Okutomi, Masatoshi},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2015},
  pages     = {199-207},
  doi       = {10.1109/ICCVW.2015.35},
  url       = {https://mlanthology.org/iccvw/2015/kim2015iccvw-joint/}
}