SOTAVerified

Visual Localization

Visual Localization is the problem of estimating the camera pose of a given image relative to a visual representation of a known scene.

Source: Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 402 papers

TitleStatusHype
LightLoc: Learning Outdoor LiDAR Localization at Light SpeedCode2
GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure DetectionCode2
DKM: Dense Kernelized Feature Matching for Geometry EstimationCode2
3D Line Mapping RevisitedCode2
GLACE: Global Local Accelerated Coordinate EncodingCode2
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural NetworkCode2
Improving Feature-based Visual Localization by Geometry-Aided MatchingCode2
GSLoc: Efficient Camera Pose Refinement via 3D Gaussian SplattingCode2
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual LocalizationCode2
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language ModelsCode2
Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmarkCode2
LiSA: LiDAR Localization with Semantic AwarenessCode2
R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual LocalizationCode2
DiffLoc: Diffusion Model for Outdoor LiDAR LocalizationCode2
LiteVLoc: Map-Lite Visual Localization for Image Goal NavigationCode2
MegaLoc: One Retrieval to Place Them AllCode2
MeshLoc: Mesh-Based Visual LocalizationCode2
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic DataCode1
Geometric Structure Aided Visual Inertial LocalizationCode1
GMMLoc: Structure Consistent Visual Localization with Gaussian Mixture ModelsCode1
A Probabilistic Framework for Visual Localization in Ambiguous ScenesCode1
FUSELOC: Fusing Global and Local Descriptors to Disambiguate 2D-3D Matching in Visual LocalizationCode1
ConDo: Continual Domain Expansion for Absolute Pose RegressionCode1
A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera RelocalizationCode1
Cross-Descriptor Visual Localization and MappingCode1
Show:102550
← PrevPage 2 of 17Next →
All datasetsOxford Radar RobotCar (Full-6)Aachen Day-Night v1.1 BenchmarkOxford RobotCar FullExtended CMU SeasonsRobotCar Seasons v2

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MapNetMean Translation Error48.21—Unverified
2PointNetVLADMean Translation Error28.48—Unverified
3DCPMean Translation Error18.45—Unverified
4AD-MapNetMean Translation Error18.43—Unverified
5AtLoc+Mean Translation Error17.92—Unverified
6PosePNMean Translation Error16.32—Unverified
7VMLocMean Translation Error15.11—Unverified
8MS-TransformerMean Translation Error11.69—Unverified
9PoseMinkLocMean Translation Error11.2—Unverified
10PosePN++Mean Translation Error10.64—Unverified
#ModelMetricClaimedVerifiedStatus
1GIM-LoFTRAcc@0.25m, 2°79.1—Unverified
2LoFTRAcc@0.25m, 2°78.5—Unverified
3GIM-SuperGlueAcc@0.25m, 2°78—Unverified
4GIM-DKMAcc@0.25m, 2°77—Unverified
5SuperGlueAcc@0.25m, 2°77—Unverified
6SCFeatAcc@0.25m, 2°74.3—Unverified
7DKMAcc@0.25m, 2°70.2—Unverified
#ModelMetricClaimedVerifiedStatus
1AtLocMean Translation Error29.6—Unverified
2MapNet++Mean Translation Error29.5—Unverified
3GNNMapNetMean Translation Error17.35—Unverified
4CoordiNetMean Translation Error14.96—Unverified
5AtLoc+Mean Translation Error13.7—Unverified
6RobustLocMean Translation Error9.37—Unverified
#ModelMetricClaimedVerifiedStatus
1Patch-NetVLADAcc @ .25m, 2°0.12—Unverified
#ModelMetricClaimedVerifiedStatus
1Patch-NetVLADAcc @ .25m, 2°0.1—Unverified