Joint Estimation of Motion, Structure and Geometry
from Stereo Sequences
1Mathematical Image Analysis Group, Saarland University, Germany
2Max-Planck Institute for Informatics, Saarbrücken, Germany
We present a novel variational method for the simultaneous estimation
of dense scene flow and structure from stereo sequences. In contrast to existing
approaches that rely on a fully calibrated camera setup, we assume that only the
intrinsic camera parameters are known. To couple the estimation of motion, structure
and geometry, we propose a joint energy functional that integrates spatial and
temporal information from two subsequent image pairs subject to an unknown
stereo setup.We further introduce a normalisation of image and stereo constraints
such that deviations from model assumptions can be interpreted in a geometrical
way. Finally, we suggest a separate discontinuity-preserving regularisation to improve
the accuracy. Experiments on calibrated and uncalibrated data demonstrate
the excellent performance of our approach.We even outperformrecent techniques
for the rectified case that make explicit use of the simplified geometry.
This is the supplementary material page for our paper Joint Estimation of Motion,
Structure and Geometry from Stereo Sequences which will be presented at the 11th European Conference on Computer Vision (ECCV 2010).
The paper can be downloaded here.
The aim of these pages is to provide additional results that did not fit in the paper.
Additionally, we provide our selfmade test sequence for download.
Please choose one of the following topics: