TR2014-013

Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting


    •  Ni, J., Marks, T.K., Tuzel, O., Porikli, F., "Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting", IEEE Winter Conference on Applications of Computer Vision (WACV), March 2014.
      BibTeX TR2014-013 PDF
      • @inproceedings{Ni2014mar,
      • author = {Ni, J. and Marks, T.K. and Tuzel, O. and Porikli, F.},
      • title = {Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting},
      • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
      • year = 2014,
      • month = mar,
      • url = {https://www.merl.com/publications/TR2014-013}
      • }
  • MERL Contact:
  • Research Area:

    Computer Vision

TR Image
Sample input images (under various light combinations) of Scene 2
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 introduce 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