3D顕著性と幾何情報を活用した高速・スケーラブルな複数アフォーダンス検出
What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection
視覚的に復元した点群上で、深層学習による3D顕著性と幾何表現を組み合わせ、複数のアフォーダンスとその物体ポーズを高速に一度で検出する手法を提案した論文。
著者: Eduardo Ruiz, Walterio Mayol-Cuevas
分類: cs.CV, cs.RO
原文アブストラクト
This paper develops and evaluates a novel method that allows for the detection of affordances in a scalable and multiple-instance manner on visually recovered pointclouds. Our approach has many advantages over alternative methods, as it is based on highly parallelizable, one-shot learning that is fast in commodity hardware. The approach is hybrid in that it uses a geometric representation together with a state-of-the-art deep learning method capable of identifying 3D scene saliency. The geometric component allows for a compact and efficient representation, boosting the performance of the deep network architecture which proved insufficient on its own. Moreover, our approach allows not only to predict whether an input scene affords or not the interactions, but also the pose of the objects that allow these interactions to take place. Our predictions align well with crowd-sourced human judgment as they are preferred with 87% probability, show high rates of improvement with almost four times (4x) better performance over a deep learning-only baseline and are seven times (7x) faster than previous art.
関連論文
- 確率的プロトタイプによる3D点群上の解釈可能なアフォーダンス検出アフォーダンス検出
- 知識蒸留とテキスト-点相関を用いたオープンボキャブラリ・アフォーダンス検出アフォーダンス検出
- 3D点群におけるオープンボキャブラリ・アフォーダンス検出アフォーダンス検出
- 動的ツリーカプセルネットワークによるアフォーダンス検出アフォーダンス検出
- 一人称視点での幾何学駆動型ワンショット・アフォーダンス検出アフォーダンス検出
- AffordanceNet:物体のアフォーダンス検出のためのエンドツーエンド深層学習手法アフォーダンス検出
