TY - JOUR
T1 - From spatiotemporal curves to reconstructed depth
AU - Rodrigues, R.
AU - Fernandes, A.
AU - Overveld, van, C.W.A.M.
AU - Ernst, F.
PY - 2004
Y1 - 2004
N2 - We present a novel approach for 3D reconstruction based on a set of images taken from a static scene. Our solution is inspired by the spatiotemporal analysis of video sequences. The method is based on a best fitting scheme for spatiotemporal curves that allows us to compute 3D world coordinates of points within the scene. As opposed to a large number of current methods, our technique deals with random camera movements in a transparent way, and even performs better in these cases than with restrained motion such as pure translation. Robustness against occlusion and aliasing is inherent to the method as well.
AB - We present a novel approach for 3D reconstruction based on a set of images taken from a static scene. Our solution is inspired by the spatiotemporal analysis of video sequences. The method is based on a best fitting scheme for spatiotemporal curves that allows us to compute 3D world coordinates of points within the scene. As opposed to a large number of current methods, our technique deals with random camera movements in a transparent way, and even performs better in these cases than with restrained motion such as pure translation. Robustness against occlusion and aliasing is inherent to the method as well.
U2 - 10.1016/j.imavis.2004.03.007
DO - 10.1016/j.imavis.2004.03.007
M3 - Article
SN - 0262-8856
VL - 22
SP - 959
EP - 970
JO - Image and Vision Computing
JF - Image and Vision Computing
IS - 12
ER -