Shape and Motion under Varying Illumination: Unifying Structure from Motion, Photometric Stereo, and Multi-view Stereo

  • Authors:
  • Li Zhang;Brian Curless;Aaron Hertzmann;Steven M. Seitz

  • Affiliations:
  • -;-;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00



This paper presents an algorithm for computing optical flow,shape, motion, lighting, and albedo from an image sequenceof a rigidly-moving Lambertian object under distant illumination.The problem is formulated in a manner that subsumesstructure from motion, multi-view stereo, and photometricstereo as special cases. The algorithm utilizes bothspatial and temporal intensity variation as cues: the formerconstrains flow and the latter constrains surface orientation;combining both cues enables dense reconstruction ofboth textured and texture-less surfaces. The algorithm worksby iteratively estimating affine camera parameters, illumination,shape, and albedo in an alternating fashion. Results aredemonstrated on videos of hand-held objects moving in frontof a fixed light and camera.