Detecting 3D Geometric Boundaries of Indoor Scenes Under Varying Lighting
Abstract
The goal of this research is to identify 3D geometric boundaries in a set of 2D photographs of a static indoor scene under unknown, changing lighting conditions. A 3D geometric boundary is a contour located at a 3D depth discontinuity or a discontinuity in the surface normal. These boundaries can be used effectively for reasoning about the 3D layout of a scene. To distinguish 3D geometric boundaries from 2D texture edges, we analyze the illumination subspace of local appearance at each image location. In indoor time-lapse photography and surveillance video, we frequently see images that are lit by unknown combinations of uncalibrated light sources. We in-troduce an algorithm for semi-binary non-negative matrix factorization (SBNMF) to decompose such images into a set of lighting basis images, each of which shows the scene lit by a single light source. These basis images provide a natural, succinct representation of the scene, enabling tasks such as scene editing (e.g., relighting) and shadow edge identification
Cite
Text
Ni et al. "Detecting 3D Geometric Boundaries of Indoor Scenes Under Varying Lighting." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6836125Markdown
[Ni et al. "Detecting 3D Geometric Boundaries of Indoor Scenes Under Varying Lighting." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/ni2014wacv-detecting/) doi:10.1109/WACV.2014.6836125BibTeX
@inproceedings{ni2014wacv-detecting,
title = {{Detecting 3D Geometric Boundaries of Indoor Scenes Under Varying Lighting}},
author = {Ni, Jie and Marks, Tim K. and Tuzel, Oncel and Porikli, Fatih},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2014},
pages = {1-8},
doi = {10.1109/WACV.2014.6836125},
url = {https://mlanthology.org/wacv/2014/ni2014wacv-detecting/}
}