PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
Authors:
Top Cited Papers
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12428-12437
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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- 1 year, 1000 km: The Oxford RobotCar datasetThe International Journal of Robotics Research, 2016
- Geometrically Based Linear Iterative Clustering for Quantitative Feature CorrespondenceComputer Graphics Forum, 2016
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- ORB-SLAM: A Versatile and Accurate Monocular SLAM SystemIEEE Transactions on Robotics, 2015
- SHOT: Unique signatures of histograms for surface and texture descriptionComputer Vision and Image Understanding, 2014
- Motion Estimation for Self-Driving Cars with a Generalized Camera2013
- 3D is here: Point Cloud Library (PCL)2011
- Avoiding Confusing Features in Place Recognition2010
- Recognizing Objects in Range Data Using Regional Point Descriptors2004
- Using spin images for efficient object recognition in cluttered 3D scenesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999