Shadow Removal from Single RGB-D Images

Yao Xiao, Efstratios Tsougenis, Chi-Keung Tang

CVPR 2014

doi:10.1109/CVPR.2014.385 /cvpr/2014/xiao2014cvpr-shadow/

Abstract

We present the first automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modified nonlocal matching is used to compute a shadow confidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets.

PDF CVPR Semantic Scholar

Cite

Text

Xiao et al. "Shadow Removal from Single RGB-D Images." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.385

Markdown

[Xiao et al. "Shadow Removal from Single RGB-D Images." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/xiao2014cvpr-shadow/) doi:10.1109/CVPR.2014.385

BibTeX

@inproceedings{xiao2014cvpr-shadow,
  title     = {{Shadow Removal from Single RGB-D Images}},
  author    = {Xiao, Yao and Tsougenis, Efstratios and Tang, Chi-Keung},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.385},
  url       = {https://mlanthology.org/cvpr/2014/xiao2014cvpr-shadow/}
}