Paper
R. Szeliski and S.B. Kang, ``Shape ambiguities in structure from
motion,'' to appear in IEEE Trans. on Pattern Analysis and Machine
Intelligence.
Abstract
This paper examines the fundamental ambiguities and uncertainties inherent
in recovering structure from motion. By examining the eigenvectors
associated with null or small eigenvalues of the Hessian matrix, we can
quantify the exact nature of these ambiguities and predict how they
affect the accuracy of the reconstructed shape. Our results for
orthographic cameras show that the bas-relief ambiguity is significant even
with many images, unless a large amount of rotation is present. Similar
results for perspective cameras suggest that three or more frames and
a large amount of rotation are required for metrically accurate
reconstruction.