構造と意味を活用した教師なし単眼深度・自己運動学習
Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics
物体ごとの3D運動を深度・自己運動と同時に学習し、動的な場面でも高精度に単眼カメラから深度と自己運動を推定する手法を提案した。
著者: Vincent Casser, Soeren Pirk, Reza Mahjourian, Anelia Angelova
分類: cs.CV, cs.RO
原文アブストラクト
We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically, we model the motion of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. [AAAI'19]. Code and models have been open sourced at https://sites.google.com/corp/view/struct2depth.
