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
Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures—0
Evaluating Attribute Confusion in Fashion Text-to-Image Generation—0
MatChA: Cross-Algorithm Matching with Feature Augmentation—0
OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic TypographyCode0
Semantic and Feature Guided Uncertainty Quantification of Visual Localization for Autonomous Vehicles—0
Hierarchical Image Matching for UAV Absolute Visual Localization via Semantic and Structural Constraints—0
Robust Visual Localization via Semantic-Guided Multi-Scale Transformer—0
Deep Learning Reforms Image Matching: A Survey and Outlook—0
Why Not Replace? Sustaining Long-Term Visual Localization via Handcrafted-Learned Feature Collaboration on CPUCode1
To Glue or Not to Glue? Classical vs Learned Image Matching for Mobile Mapping Cameras to Textured Semantic 3D Building ModelsCode0
LiftFeat: 3D Geometry-Aware Local Feature MatchingCode3
SafeNav: Safe Path Navigation using Landmark Based Localization in a GPS-denied Environment—0
GSFeatLoc: Visual Localization Using Feature Correspondence on 3D Gaussian Splatting—0
Visual Re-Ranking with Non-Visual Side InformationCode0
Re-thinking Temporal Search for Long-Form Video UnderstandingCode2
LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds—0
Scene-agnostic Pose Regression for Visual Localization—0
Selecting and Pruning: A Differentiable Causal Sequentialized State-Space Model for Two-View Correspondence Learning—0
LightLoc: Learning Outdoor LiDAR Localization at Light SpeedCode2
A-SCoRe: Attention-based Scene Coordinate Regression for wide-ranging scenariosCode0
Multi-Platform Teach-and-Repeat Navigation by Visual Place Recognition Based on Deep-Learned Local Features—0
Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a BenchmarkCode2
NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features—0
Geometry-Constrained Monocular Scale Estimation Using Semantic Segmentation for Dynamic Scenes—0
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
MegaLoc: One Retrieval to Place Them AllCode2
3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments—0
Imit Diff: Semantics Guided Diffusion Transformer with Dual Resolution Fusion for Imitation Learning—0
Visual Localization via Semantic Structures in Autonomous Photovoltaic Power Plant Inspection—0
GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian SplattingCode2
FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis—0
Training Medical Large Vision-Language Models with Abnormal-Aware Feedback—0
R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual LocalizationCode2
Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization—0
GPVK-VL: Geometry-Preserving Virtual Keyframes for Visual Localization under Large Viewpoint Changes—0
CroCoDL: Cross-device Collaborative Dataset for Localization—0
ConDo: Continual Domain Expansion for Absolute Pose RegressionCode1
Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual LocalizationCode3
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Mutli-View 3D Reconstruction using Knowledge DistillationCode0
Unleashing the Power of Data Synthesis in Visual Localization—0
PEnG: Pose-Enhanced Geo-LocalisationCode0
OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic GuidanceCode2
YOWO: You Only Walk Once to Jointly Map An Indoor Scene and Register Ceiling-mounted Cameras—0
Leveraging Spatial Attention and Edge Context for Optimized Feature Selection in Visual Localization—0
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe AlignmentCode2
LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images—0
RNR-Nav: A Real-World Visual Navigation System Using Renderable Neural Radiance Maps—0
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