InLoc

Dataset Information
Modalities
Images
License
Unknown
Homepage

Overview

InLoc is a dataset with reference 6DoF poses for large-scale indoor localization. Query photographs are captured by mobile phones at a different time than the reference 3D map, thus presenting a realistic indoor localization scenario.

Source: InLoc: Indoor Visual Localization with Dense Matching and View Synthesis

Variants: InLoc

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Pose Estimation GIM-DKM GIM: Learning Generalizable Image Matcher … 2024-02-16
Pose Estimation GIM-LoFTR GIM: Learning Generalizable Image Matcher … 2024-02-16
Pose Estimation GIM-SuperGlue GIM: Learning Generalizable Image Matcher … 2024-02-16
Pose Estimation DKM DKM: Dense Kernelized Feature Matching … 2022-02-01
Pose Estimation LoFTR LoFTR: Detector-Free Local Feature Matching … 2021-04-01
Pose Estimation SuperGlue SuperGlue: Learning Feature Matching with … 2019-11-26

Research Papers

Recent papers with results on this dataset: