点群分類のための幾何学的逆投影ネットワーク
Geometric Back-projection Network for Point Cloud Classification
低次元3D空間で点の幾何情報を明示的に豊かにし、高次元特徴空間でCNN構造を用いて局所幾何文脈を暗黙的に学習する点群分類ネットワークを提案。誤り訂正フィードバック構造とチャネル親和性に基づくアテンションで精度と効率のバランスを実現した。
著者: Shi Qiu, Saeed Anwar, Nick Barnes
分類: cs.CV, cs.LG, cs.RO, eess.IV
原文アブストラクト
As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better representations. To achieve this, on the one hand, we enrich the geometric information of points in low-level 3D space explicitly. On the other hand, we apply CNN-based structures in high-level feature spaces to learn local geometric context implicitly. Specifically, we leverage an idea of error-correcting feedback structure to capture the local features of point clouds comprehensively. Furthermore, an attention module based on channel affinity assists the feature map to avoid possible redundancy by emphasizing its distinct channels. The performance on both synthetic and real-world point clouds datasets demonstrate the superiority and applicability of our network. Comparing with other state-of-the-art methods, our approach balances accuracy and efficiency.
