Temporally coherent 4D reconstruction of complex dynamic scenes
Armin Mustafa, Hansung Kim, Jean-Yves Guillemaut and Adrian Hilton Centre for Vision, Speech & Signal Processing University of Surrey, United Kingdom appeared atIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 (ORAL)
Abstract
This paper presents an approach for reconstruction of 4D temporally coherent models of complex dynamic scenes. No prior knowledge is required of scene structure or camera calibration allowing reconstruction from multiple moving cameras. Sparse-to-dense temporal correspondence is integrated with joint multi-view segmentation and reconstruction to obtain a complete 4D representation of static and dynamic objects. Temporal coherence is exploited to overcome visual ambiguities resulting in improved reconstruction of complex scenes. Robust joint segmentation and reconstruction of dynamic objects is achieved by introducing a geodesic star convexity constraint. Comparative evaluation is performed on a variety of unstructured indoor and outdoor dynamic scenes with hand-held cameras and multiple people. This demonstrates reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction.
Paper
Temporally coherent 4D reconstruction of complex dynamic scenes
Armin Mustafa, Hansung Kim, Jean-Yves Guillemaut and Adrian Hilton
CVPR 2016
Data
Data used in this work can be found in the CVSSP 3D Data Repository.Citation
@INPROCEEDINGS{Mustafa16,
title = {Temporally coherent 4D reconstruction of complex dynamic scenes},
year={2016},
booktitle={CVPR},
author={Mustafa, A. and Kim, H. and Guillemaut, J-Y. and Hilton, A.}
}