日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

3D記述子arXiv:1808.10322

PPF-FoldNet:回転不変な3D局所記述子の教師なし学習

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

シェア:XThreadsFacebookLINEはてブBluesky

点対特徴の折り畳み型オートエンコーダにより、教師なしで回転不変な3D局所記述子を学習する手法を提案し、回転や点密度変化に頑健であることを示した。

著者: Haowen Deng, Tolga Birdal, Slobodan Ilic

分類: cs.CV, cs.CG, cs.LG, cs.RO

原文アブストラクト

We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates neither supervision, nor a sensitive local reference frame, benefits from point-set sparsity, is end-to-end, fast, and can extract powerful rotation invariant descriptors. Thanks to a novel feature visualization, its evolution can be monitored to provide interpretable insights. Our extensive experiments demonstrate that despite having six degree-of-freedom invariance and lack of training labels, our network achieves state of the art results in standard benchmark datasets and outperforms its competitors when rotations and varying point densities are present. PPF-FoldNet achieves $9\%$ higher recall on standard benchmarks, $23\%$ higher recall when rotations are introduced into the same datasets and finally, a margin of $>35\%$ is attained when point density is significantly decreased.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI