OpenCodePapers

visual-localization-on-aachen-day-night-v1-1

Visual Localization
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAcc@0.25m, 2°Acc@0.5m, 5°Acc@5m, 10°ModelNameReleaseDate
Learning to Produce Semi-dense Correspondences for Visual Localization✓ Link87.893.9100.0DeViLoc2024-02-13
SemLight: Distilled Semantic–Geometric Fusion for Efficient Local Feature Matching81.788.5SemLight2026-09-08
TextFM: Robust Semi-dense Feature Matching with Language Guidance79.892.099.5TextFM2026-06-03
GIM: Learning Generalizable Image Matcher From Internet Videos✓ Link79.191.6100.0GIM-LoFTR2024-02-16
LoFTR: Detector-Free Local Feature Matching with Transformers✓ Link78.590.699.0LoFTR2021-04-01
GIM: Learning Generalizable Image Matcher From Internet Videos✓ Link78.090.6100.0GIM-SuperGlue2024-02-16
SuperGlue: Learning Feature Matching with Graph Neural Networks✓ Link77.090.6100.0SuperGlue2019-11-26
GIM: Learning Generalizable Image Matcher From Internet Videos✓ Link77.090.199.5GIM-DKM2024-02-16
Shared Coupling-bridge for Weakly Supervised Local Feature Learning✓ Link74.38998.4SCFeat2022-12-14
Absolute Pose from One or Two Scaled and Oriented Features✓ Link71.7P2ORI2024-06-17
XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher✓ Link70.4082.4090.32XFeat Reproduced2026-08-10
DKM: Dense Kernelized Feature Matching for Geometry Estimation✓ Link70.290.197.4DKM2022-02-01
Absolute Pose from One or Two Scaled and Oriented Features✓ Link88.0UP1SIFT2024-06-17
CoLoR: The Devil is in Scene Coordinate Regression for Large-Scale Visual Localization67.388.8CoLoR2026-06-03
Gravity-aware partially calibrated absolute pose estimation from affine- or rotation-covariant features60.280.197.4UP1PfAC2026-08-20