TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
3D Place Recognition	Oxford RobotCar Dataset	PCAN	AR@1%	83.8	# 9
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (refined)	recall@top1%	86.4	# 20
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (refined)	recall@top1	70.72	# 18
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (baseline)	recall@top1%	83.81	# 22
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (baseline)	recall@top1	69.05	# 19

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pcan-3d-attention-map-learning-using/3d-place-recognition-on-oxford-robotcar)](https://paperswithcode.com/sota/3d-place-recognition-on-oxford-robotcar?p=pcan-3d-attention-map-learning-using)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pcan-3d-attention-map-learning-using/point-cloud-retrieval-on-oxford-robotcar)](https://paperswithcode.com/sota/point-cloud-retrieval-on-oxford-robotcar?p=pcan-3d-attention-map-learning-using)`

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

CVPR 2019 · Wenxiao Zhang, Chunxia Xiao ·

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.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Code

Add Remove Mark official

XLechter/PCAN official

Tasks

Add Remove

3D Place Recognition

Point Cloud Retrieval

Retrieval

Visual Place Recognition

Datasets

Oxford RobotCar Dataset

Results from the Paper

Edit

Ranked #9 on 3D Place Recognition on Oxford RobotCar Dataset (AR@1% metric)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
3D Place Recognition	Oxford RobotCar Dataset	PCAN	AR@1%	83.8	# 9	Compare
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (refined)	recall@top1%	86.4	# 20	Compare
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (refined)	recall@top1	70.72	# 18	Compare
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (baseline)	recall@top1%	83.81	# 22	Compare
Point Cloud Retrieval	Oxford RobotCar (LiDAR 4096 points)	PCAN (baseline)	recall@top1	69.05	# 19	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

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

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove