SVT-Net

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Visual Place RecognitiononOxford RobotCar Dataset
AR@1· 2021-05-01
93.7
best: 94.36 (CrossLoc3D)
SOTA
SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition arXiv:2105.00149
Visual Place RecognitiononOxford RobotCar Dataset
AR@1%· 2021-05-01
97.8
best: 98.59 (CrossLoc3D)
SOTA
SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition arXiv:2105.00149