Joint Estimation of Motion, Structure and Geometry from Stereo Sequences - Mathematical Image Analysis Group, Saarland University

Supplementary Material Page

Joint Estimation of Motion, Structure and Geometry from Stereo Sequences

ECCV 2010

Levi Valgaerts¹, Andrés Bruhn¹, Henning Zimmer¹, Joachim Weickert¹,
Carsten Stoll², Christian Theobalt²

¹Mathematical Image Analysis Group, Saarland University, Germany
²Max-Planck Institute for Informatics, Saarbrücken, Germany

Abstract
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:

Additional Results

Download our Test Sequence