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 51–100 of 402 papers

TitleStatusHype
FUSELOC: Fusing Global and Local Descriptors to Disambiguate 2D-3D Matching in Visual LocalizationCode1
Multicam-SLAM: Non-overlapping Multi-camera SLAM for Indirect Visual Localization and NavigationCode1
SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen EnvironmentsCode1
Leveraging Neural Radiance Field in Descriptor Synthesis for Keypoints Scene Coordinate RegressionCode1
BEV-CV: Birds-Eye-View Transform for Cross-View Geo-LocalisationCode1
360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device QueriesCode1
FocusTune: Tuning Visual Localization through Focus-Guided SamplingCode1
CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective InvariantsCode1
Segment Anything Model is a Good Teacher for Local Feature LearningCode1
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual LocalizationCode1
Prompting Segmentation with Sound Is Generalizable Audio-Visual Source LocalizerCode1
OFVL-MS: Once for Visual Localization across Multiple Indoor ScenesCode1
D2S: Representing sparse descriptors and 3D coordinates for camera relocalizationCode1
ResMatch: Residual Attention Learning for Local Feature MatchingCode1
S2LD: Sparse-to-Local-Dense Matching for Geometry-Guided Correspondence EstimationCode1
SFD2: Semantic-guided Feature Detection and DescriptionCode1
Attention Weighted Local DescriptorsCode1
NeRF-Loc: Visual Localization with Conditional Neural Radiance FieldCode1
3DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and DatasetCode1
Visual Localization using Imperfect 3D Models from the InternetCode1
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic FusionCode1
Data-efficient Large Scale Place Recognition with Graded Similarity SupervisionCode1
Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative KeypointsCode1
Renderable Neural Radiance Map for Visual NavigationCode1
A Probabilistic Framework for Visual Localization in Ambiguous ScenesCode1
SGLoc: Scene Geometry Encoding for Outdoor LiDAR LocalizationCode1
Privacy-Preserving Visual Localization with Event CamerasCode1
SliceMatch: Geometry-guided Aggregation for Cross-View Pose EstimationCode1
RobustLoc: Robust Camera Pose Regression in Challenging Driving EnvironmentsCode1
LaLaLoc++: Global Floor Plan Comprehension for Layout Localisation in Unvisited EnvironmentsCode1
GSV-Cities: Toward Appropriate Supervised Visual Place RecognitionCode1
Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature DescriptorsCode1
Visual Localization via Few-Shot Scene Region ClassificationCode1
Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-LocalizationCode1
CPO: Change Robust Panorama to Point Cloud LocalizationCode1
VPAIR -- Aerial Visual Place Recognition and Localization in Large-scale Outdoor EnvironmentsCode1
LASER: LAtent SpacE Rendering for 2D Visual LocalizationCode1
Is Geometry Enough for Matching in Visual Localization?Code1
Benchmarking Visual Localization for Autonomous NavigationCode1
MatchFormer: Interleaving Attention in Transformers for Feature MatchingCode1
ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision DiscretizationCode1
PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local DescriptorsCode1
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic DataCode1
Line as a Visual Sentence: Context-aware Line Descriptor for Visual LocalizationCode1
Continual Learning for Image-Based Camera LocalizationCode1
PICCOLO: Point Cloud-Centric Omnidirectional LocalizationCode1
RoadMap: A Light-Weight Semantic Map for Visual Localization towards Autonomous DrivingCode1
VS-Net: Voting with Segmentation for Visual LocalizationCode1
Probabilistic Visual Place Recognition for Hierarchical LocalizationCode1
LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited EnvironmentsCode1
Show:102550
← PrevPage 2 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
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