3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles International Journal of Computer Vision Year : 2008

3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination

Abstract

We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can be thought of as extending classical multi-view stereo to cases where point correspondence cannot be established, or extending classical shape from shading to the case of multiple views with unknown light sources. We show that a first naive formalization of this problem yields algorithms that are numerically unstable, no matter how close the initialization is to the true geometry. We then propose a computational scheme to overcome this problem, resulting in provably stable algorithms that converge to (local) minima of the cost functional. We develop a new model that explicitly enforces positivity in the light sources with the assumption that the object is Lambertian and its albedo is piecewise constant and show that the new model significantly improves the accuracy and robustness relative to existing approaches.
Vignette du fichier
img.jpg (58.56 Ko) Télécharger le fichier Fichier principal
Vignette du fichier
Jin-Wang-Cremers-Prados-Yezzi-soatto-jicv-2007.pdf (528.39 Ko) Télécharger le fichier
Format : Figure, Image
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00260433 , version 1 (04-03-2008)

Identifiers

Cite

Hailin Jin, Daniel Cremers, Dejun Wang, Emmanuel Prados, Anthony Yezzi, et al.. 3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination. International Journal of Computer Vision, 2008, 76 (3), pp.245-256. ⟨10.1007/s11263-007-0055-y⟩. ⟨inria-00260433⟩
433 View
527 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More