Discovering Point Lights with Intensity Distance Fields
1 University of Washington
2 Facebook Inc.
We introduce the light localization problem. A scene is illuminated by a
set of unobserved isotropic point lights. Given the geometry, materials, and
illuminated appearance of the scene, the light localization problem is to
completely recover the number, positions, and intensities of the
lights. We first present a scene transform that identifies likely light positions.
Based on this transform, we develop an iterative algorithm to locate remaining
lights and determine all light intensities. We demonstrate the
success of this method in a large set of 2D synthetic scenes, and show that
it extends to 3D, in both synthetic scenes and real-world scenes.
Edward Zhang, Michael F. Cohen, and Brian Curless. 2018.
"Discovering Point Lights with Intensity Distance Fields"
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
This work was supported by the NSF/Intel Visual and Experiential Computing Award
#1538618, with additional support from Google and the University of Washington Reality Lab.