We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences. In contrast to the competing methods, we take advantage of an oversegmentation of the reference frame and robust optimization techniques. We formulate scene flow recovery as a global non-linear least squares problem which is iteratively solved by a damped Gauss-Newton approach. As a result, we obtain a qualitatively new level of accuracy in RGB-D based scene flow estimation which can potentially run in real-time. Our method can handle challenging cases with rigid, piecewise rigid, articulated and moderate non-rigid motion, and does not rely on prior knowledge about the types of motions and deformations. Extensive experiments on synthetic and real data show that our method outperforms state-of-the-art.
@article{arxiv.1710.02124,
title = {Multiframe Scene Flow with Piecewise Rigid Motion},
author = {Vladislav Golyanik and Kihwan Kim and Robert Maier and Matthias Nießner and Didier Stricker and Jan Kautz},
journal= {arXiv preprint arXiv:1710.02124},
year = {2017}
}
Comments
International Conference on 3D Vision (3DV), Qingdao, China, October 2017