In this paper we tackle the problem of scene flow estimation in the context of self-driving. We leverage deep learning techniques as well as strong priors as in our application domain the motion of the scene can be composed by the motion of the robot and the 3D motion of the actors in the scene. We formulate the problem as energy minimization in a deep structured model, which can be solved efficiently in the GPU by unrolling a Gaussian-Newton solver. Our experiments in the challenging KITTI scene flow dataset show that we outperform the state-of-the-art by a very large margin, while being 800 times faster.
@article{arxiv.1904.08913,
title = {Deep Rigid Instance Scene Flow},
author = {Wei-Chiu Ma and Shenlong Wang and Rui Hu and Yuwen Xiong and Raquel Urtasun},
journal= {arXiv preprint arXiv:1904.08913},
year = {2019}
}
Comments
CVPR 2019. Rank 1st on KITTI scene flow benchmark. 800 times faster than prior art