実時間オープンセットシーン理解のための特徴量リアリスティックニューラル融合
Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding
事前学習済みネットワークの汎用特徴量をリアルタイムSLAM中の3D幾何ニューラル場に融合し、実行時の少量のラベル付けで未知物体も高精度にセグメンテーションできる手法を提案。
著者: Kirill Mazur, Edgar Sucar, Andrew J. Davison
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which fuses general learned features from a standard pre-trained network into a highly efficient 3D geometric neural field representation during real-time SLAM. The fused 3D feature maps inherit the coherence of the neural field's geometry representation. This means that tiny amounts of human labelling interacting at runtime enable objects or even parts of objects to be robustly and accurately segmented in an open set manner.
