深層剛体インスタンスシーンフロー
Deep Rigid Instance Scene Flow
自動運転向けに、深層学習と剛体運動の事前知識を組み合わせたシーンフロー推定手法を提案し、KITTIで高精度かつ800倍高速化を実現した。
著者: Wei-Chiu Ma, Shenlong Wang, Rui Hu, Yuwen Xiong, Raquel Urtasun
分類: cs.CV, cs.RO
原文アブストラクト
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.
