3つの要点 ✔️ 2D検出器に頼ることなく生データを直接3Dターゲット検出が可能 ✔️ 点群ネットワークに古典的なハフ変換に似た投票メカニズムであるVoteNetを提案 ✔️ 従来手法の多くを凌駕した Deep Hough Voting for 3D Object Detection in Point Clouds written by Charles R. Qi, Or Litany, Kaiming He, Leonidas J. Guibas (Submitted on 21 Apr 2019 (v1), last revised 22 Aug 2019 (this version, v2)) Comments: Published by ICCV 2019 Subjects: Computer Vision and Pattern Recognition (cs.CV) はじめに
![点群における3Dターゲット検出の新しいフレームワークVoteNet、2つのデータセットで最高精度を更新](https://cdn-ak-scissors.b.st-hatena.com/image/square/0b303ae9573dad8d60a43469877982f23bdd2c9b/height=288;version=1;width=512/https%3A%2F%2Faisholar.s3.ap-northeast-1.amazonaws.com%2Fmedia%2FJune2020%2F%25E7%2582%25B9%25E7%25BE%25A4%25E5%25AD%25A6%25E7%25BF%2592%25E3%2583%25A2%25E3%2583%2587%25E3%2583%25AB%25E3%2581%25AB%25E6%258A%2595%25E7%25A5%25A8%25E3%2583%25A1%25E3%2582%25AB%25E3%2583%258B%25E3%2582%25BA%25E3%2583%25A0%25EF%25BC%259F%25EF%25BC%2581_1_.png)