Return to Research

Scene Flow Estimation

Scene Flow Estimation by Growing Correspondence Seeds

Jan Cech, Jordi Sanchez-Rieira, and Radu Horaud

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3129-3136, 2011

Abstract  | Code | HALIEEEXplore | Bibtex | Video | Papers

Software package as a Matlab toolbox (source code of binaries) available from Jan Cech’s website or here.

Abstract. A simple seed growing algorithm for estimating scene flow in a stereo setup is presented. Two calibrated and synchronized cameras observe a scene and output a sequence of image pairs. The algorithm simultaneously computes a disparity map between the image pairs and optical flow maps between consecutive images. This, together with calibration data, is an equivalent representation of the 3D scene flow, i.e. a 3D velocity vector is associated with each reconstructed point. The proposed method starts from correspondence seeds and propagates these correspondences to their neighborhood. It is accurate for complex scenes with large motions and produces temporallycoherent stereo disparity and optical flow results. The algorithm is fast due to inherent search space reduction. An explicit comparison with recent methods of spatiotemporal stereo and variational optical and scene flow is provided.



Scene Flow Estimation by Growing Correspondence Seeds. Jan Cech, Jordi Sanchez-Riera, Radu Horaud. CVPR 2011 – IEEE Conference on Computer Vision and Pattern Recognition, June 2011, Colorado Springs, United States. IEEE Computer Society, pp. 3129-3136, 2011 BibTex

Joint Disparity and Optical Flow by Correspondence Growing. Jan Cech, Radu Horaud. ICASSP 2011 – IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2011, Prague, Czech Republic. IEEE, pp.893-896, 2011. BibTex

Robust Spatiotemporal Stereo for Dynamic Scenes. Jordi Sanchez-Riera, Jan Cech, Radu Horaud. ICPR 2012 – 21st International Conference on Pattern Recognition, Nov 2012, Tsukuba Science City, Japan. IEEE, pp. 360-363, 2012. BibTex