Modelling Dynamic Scenes by Registering Multi-View Image Sequences
Authors:
- 27 July 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10636919) , 822-827
Abstract
In this paper, we present a new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences. Our method minimizes the prediction error of the shape and motion estimates. Both problems then translate into a generic image registration task. The latter is entrusted to a similarity measure chosen depending on imaging conditions and scene properties. In particular, our method can be made robust to appearance changes due to non-Lambertian materials and illumination changes. It results in a simpler, more flexible, and more efficient implementation than existing deformable surface approaches. The computation time on large datasets does not exceed thirty minutes. Moreover, our method is compliant with a hardware implementation with graphics processor units. Our stereovision algorithm yields very good results on a variety of datasets including specularities and translucency. We have successfully tested our scene flow algorithm on a very challenging multi-view video sequence of a non-rigid scene.Keywords
This publication has 14 references indexed in Scilit:
- Three-dimensional scene flowIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Wide-baseline stereo from multiple views: a probabilistic account2004
- Tales of shape and radiance in multiview stereo2003
- Dense matching of multiple wide-baseline views2003
- Multi-View Scene Capture by Surfel Sampling: From Video Streams to Non-Rigid 3D Motion, Shape and ReflectanceInternational Journal of Computer Vision, 2002
- A Theory of Shape by Space CarvingInternational Journal of Computer Vision, 2000
- Prediction error as a quality metric for motion and stereo1999
- Variational principles, surface evolution, PDEs, level set methods, and the stereo problemIEEE Transactions on Image Processing, 1998
- Alignment by Maximization of Mutual InformationInternational Journal of Computer Vision, 1997
- Fast shadows and lighting effects using texture mappingACM SIGGRAPH Computer Graphics, 1992