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 1–50 of 402 papers

TitleStatusHype
XFeat: Accelerated Features for Lightweight Image MatchingCode5
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and BeyondCode5
GeoCalib: Learning Single-image Calibration with Geometric OptimizationCode4
GIM: Learning Generalizable Image Matcher From Internet VideosCode4
LightGlue: Local Feature Matching at Light SpeedCode4
LiftFeat: 3D Geometry-Aware Local Feature MatchingCode3
Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual LocalizationCode3
UAV-VisLoc: A Large-scale Dataset for UAV Visual LocalizationCode3
Representing 3D sparse map points and lines for camera relocalizationCode3
Re-thinking Temporal Search for Long-Form Video UnderstandingCode2
LightLoc: Learning Outdoor LiDAR Localization at Light SpeedCode2
Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a BenchmarkCode2
MegaLoc: One Retrieval to Place Them AllCode2
GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian SplattingCode2
R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual LocalizationCode2
OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic GuidanceCode2
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe AlignmentCode2
LiteVLoc: Map-Lite Visual Localization for Image Goal NavigationCode2
Game4Loc: A UAV Geo-Localization Benchmark from Game DataCode2
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual LocalizationCode2
GSLoc: Efficient Camera Pose Refinement via 3D Gaussian SplattingCode2
GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure DetectionCode2
GLACE: Global Local Accelerated Coordinate EncodingCode2
Visual place recognition for aerial imagery: A surveyCode2
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language ModelsCode2
PRAM: Place Recognition Anywhere Model for Efficient Visual LocalizationCode2
Fully Geometric Panoramic LocalizationCode2
Learning to Produce Semi-dense Correspondences for Visual LocalizationCode2
UAVD4L: A Large-Scale Dataset for UAV 6-DoF LocalizationCode2
LiSA: LiDAR Localization with Semantic AwarenessCode2
DiffLoc: Diffusion Model for Outdoor LiDAR LocalizationCode2
GlueStick: Robust Image Matching by Sticking Points and Lines TogetherCode2
OrienterNet: Visual Localization in 2D Public Maps with Neural MatchingCode2
3D Line Mapping RevisitedCode2
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural NetworkCode2
Improving Feature-based Visual Localization by Geometry-Aided MatchingCode2
Neural Density-Distance FieldsCode2
MeshLoc: Mesh-Based Visual LocalizationCode2
Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmarkCode2
OnePose: One-Shot Object Pose Estimation without CAD ModelsCode2
DKM: Dense Kernelized Feature Matching for Geometry EstimationCode2
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
Why Not Replace? Sustaining Long-Term Visual Localization via Handcrafted-Learned Feature Collaboration on CPUCode1
Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater EnvironmentsCode1
EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth RegistrationCode1
A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera RelocalizationCode1
ConDo: Continual Domain Expansion for Absolute Pose RegressionCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place RecognitionCode1
SpaGBOL: Spatial-Graph-Based Orientated LocalisationCode1
Show:102550
← PrevPage 1 of 9Next →
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
4SuperGlueAcc@0.25m, 2°77—Unverified
5GIM-DKMAcc@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