Motion Cooperation: Smooth Piece-wise Rigid Scene Flow from RGB-D Images

Jaimez M, Souiai M, Stuckler J, Gonzalez-Jimenez J, Cremers D (2015)

Publication Type: Conference contribution

Publication year: 2015

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 64-72

Conference Proceedings Title: Proceedings - 2015 International Conference on 3D Vision, 3DV 2015

Event location: Lyon, FRA

ISBN: 9781467383325

DOI: 10.1109/3DV.2015.15

Abstract

We propose a novel joint registration and segmentation approach to estimate scene flow from RGB-D images. Instead of assuming the scene to be composed of a number of independent rigidly-moving parts, we use non-binary labels to capture non-rigid deformations at transitions between the rigid parts of the scene. Thus, the velocity of any point can be computed as a linear combination (interpolation) of the estimated rigid motions, which provides better results than traditional sharp piecewise segmentations. Within a variational framework, the smooth segments of the scene and their corresponding rigid velocities are alternately refined until convergence. A K-means-based segmentation is employed as an initialization, and the number of regions is subsequently adapted during the optimization process to capture any arbitrary number of independently moving objects. We evaluate our approach with both synthetic and real RGB-D images that contain varied and large motions. The experiments show that our method estimates the scene flow more accurately than the most recent works in the field, and at the same time provides a meaningful segmentation of the scene based on 3D motion.

Involved external institutions

Technische Universität München (TUM)

Germany (DE) Universidad de Málaga / University of Malaga

Spain (ES)

How to cite

APA:

Jaimez, M., Souiai, M., Stuckler, J., Gonzalez-Jimenez, J., & Cremers, D. (2015). Motion Cooperation: Smooth Piece-wise Rigid Scene Flow from RGB-D Images. In Michael Brown, Jana Kosecka, Christian Theobalt (Eds.), Proceedings - 2015 International Conference on 3D Vision, 3DV 2015 (pp. 64-72). Lyon, FRA: Institute of Electrical and Electronics Engineers Inc..

MLA:

Jaimez, Mariano, et al. "Motion Cooperation: Smooth Piece-wise Rigid Scene Flow from RGB-D Images." Proceedings of the 2015 International Conference on 3D Vision, 3DV 2015, Lyon, FRA Ed. Michael Brown, Jana Kosecka, Christian Theobalt, Institute of Electrical and Electronics Engineers Inc., 2015. 64-72.

BibTeX: Download