Visual Place Recognition
Visual Place Recognition is a task in the field of computer vision that aims to recognize locations by matching different views of the same place taken at different times. This technology is of great value in applications such as robot navigation, autonomous driving, and augmented reality, as it can enhance the environmental perception capabilities and positioning accuracy of systems.
17 Places
AmsterTime
Baidu Mall
Berlin Kudamm
HEAPUtil
CV-Cities
Eynsham
BoQ
Gardens Point
Hawkins
Inside Out
KITTI
None
KITTI360pose
MambaPlace
Laurel Caverns
Mapillary test
BoQ
Mapillary val
MixVPR
Mid-Atlantic Ridge
MSLS
ProGEO
Nardo-Air
Nardo-Air R
AnyLoc-VLAD-DINO
Nordland
SelaVPR
Oxford RobotCar Dataset
Oxford RobotCar (LiDAR 4096 points+RGB)
MinkLoc++ (LiDAR+RGB)
Pittsburgh-250k-test
DINOv2 SALAD
Pittsburgh-30k-test
Pair-VPR-p
San Francisco Landmark Dataset
BoQ
SF-XL test v1
EigenPlaces
SF-XL test v2
CosPlace
SPED
St Lucia
BoQ
SVOX-Night
SVOX-Overcast
SVOX-Rain
SVOX-Snow
SVOX-Sun
Tokyo247
SelaVPR
VP-Air
VP Air
SegVLAD-PreT (M)