PCAN: 3D Attention Map Learning Using Contextual Information For Point Cloud Based Retrieval

Abstract

Point cloud based retrieval for place recognition is an emerging problem in vision field. The main challenge is how to find an efficient way to encode the local features into a discriminative global descriptor. In this paper, we propose a Point Contextual Attention Network (PCAN), which can predict the significance of each local point feature based on point context. Our network makes it possible to pay more attention to the task-relevent features when aggregating local features. Experiments on various benchmark datasets show that the proposed network can provide outperformance than current state-of-the-art approaches.

Stats

• citations209
• S2 citations—
• github stars0
• HF likes0
• heat score17.42
• arxiv keyzhang2019pcan

Related papers

• Efficient 3D Point Cloud Feature Learning For Large-scale Place Recognition (2021)14.73
• Pointnetvlad: Deep Point Cloud Based Retrieval For Large-scale Place Recognition (2018)25.45
• Lpd-net: 3D Point Cloud Learning For Large-scale Place Recognition And Environment Analysis (2018)18.40
• Sca-pvnet: Self-and-cross Attention Based Aggregation Of Point Cloud And Multi-view For 3D Object Retrieval (2023)10.07
• Attention-based Pyramid Aggregation Network For Visual Place Recognition (2018)14.11
• Logg3d-net: Locally Guided Global Descriptor Learning For 3D Place Recognition (2021)19.02
• CAMAL: Context-aware Multi-layer Attention Framework For Lightweight Environment Invariant Visual Place Recognition (2019)0.00
• CSCPR: Cross-source-context Indoor RGB-D Place Recognition (2024)0.00