ML Anthology

Fast Spatially-Varying Indoor Lighting Estimation

Mathieu Garon, Kalyan Sunkavalli, Sunil Hadap, Nathan Carr, Jean-Francois Lalonde
CVPR 2019
doi:10.1109/CVPR.2019.00707 /cvpr/2019/garon2019cvpr-fast/

Abstract

We propose a real-time method to estimate spatially-varying indoor lighting from a single RGB image. Given an image and a 2D location in that image, our CNN estimates a 5th order spherical harmonic representation of the lighting at the given location in less than 20ms on a laptop mobile graphics card. While existing approaches estimate a single, global lighting representation or require depth as input, our method reasons about local lighting without requiring any geometry information. We demonstrate, through quantitative experiments including a user study, that our results achieve lower lighting estimation errors and are preferred by users over the state-of-the-art. Our approach can be used directly for augmented reality applications, where a virtual object is relit realistically at any position in the scene in real-time.

PDF CVPR Semantic Scholar

Cite

Text

Garon et al. "Fast Spatially-Varying Indoor Lighting Estimation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00707

Markdown

[Garon et al. "Fast Spatially-Varying Indoor Lighting Estimation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/garon2019cvpr-fast/) doi:10.1109/CVPR.2019.00707

BibTeX

@inproceedings{garon2019cvpr-fast,
  title     = {{Fast Spatially-Varying Indoor Lighting Estimation}},
  author    = {Garon, Mathieu and Sunkavalli, Kalyan and Hadap, Sunil and Carr, Nathan and Lalonde, Jean-Francois},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00707},
  url       = {https://mlanthology.org/cvpr/2019/garon2019cvpr-fast/}
}