Sciweavers

ICCV
2003
IEEE

Tales of Shape and Radiance in Multi-view Stereo

15 years 1 months ago
Tales of Shape and Radiance in Multi-view Stereo
To what extent can three-dimensional shape and radiance be inferred from a collection of images? Can the two be estimated separately while retaining optimality? How should the optimality criterion be computed? When is it necessary to employ an explicit model of the reflectance properties of a scene? In this paper we introduce a separation principle for shape and radiance estimation that applies to Lambertian scenes and holds for any choice of norm. When the scene is not Lambertian, however, shape cannot be decoupled from radiance, and therefore matching image-to-image is not possible directly. We employ a rank constraint on the radiance tensor, which is commonly used in computer graphics, and construct a novel cost functional whose minimization leads to an estimate of both shape and radiance for non-Lambertian objects, which we validate experimentally.
Stefano Soatto, Anthony J. Yezzi, Hailin Jin
Added 15 Oct 2009
Updated 31 Oct 2009
Type Conference
Year 2003
Where ICCV
Authors Stefano Soatto, Anthony J. Yezzi, Hailin Jin
Comments (0)