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

Showing 351375 of 402 papers

TitleStatusHype
OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic TypographyCode0
Optimizing Fiducial Marker Placement for Improved Visual LocalizationCode0
Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood InformationCode0
Eiffel Tower: A Deep-Sea Underwater Dataset for Long-Term Visual LocalizationCode0
Night-to-Day Image Translation for Retrieval-based LocalizationCode0
Neural-Guided RANSAC: Learning Where to Sample Model HypothesesCode0
Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environmentCode0
Neighbourhood Consensus NetworksCode0
Soft Expectation and Deep Maximization for Image Feature DetectionCode0
Mutli-View 3D Reconstruction using Knowledge DistillationCode0
Render-and-Compare: Cross-View 6 DoF Localization from Noisy PriorCode0
LiDAR-based localization using universal encoding and memory-aware regressionCode0
DSAC - Differentiable RANSAC for Camera LocalizationCode0
Leveraging Deep Visual Descriptors for Hierarchical Efficient LocalizationCode0
Learning to Localize in New Environments from Synthetic Training DataCode0
Sparse-to-Dense Hypercolumn Matching for Long-Term Visual LocalizationCode0
Reuse your features: unifying retrieval and feature-metric alignmentCode0
Visual Servoing of Unmanned Surface Vehicle from Small Tethered Unmanned Aerial VehicleCode0
Learning Matchable Image Transformations for Long-term Metric Visual LocalizationCode0
A-SCoRe: Attention-based Scene Coordinate Regression for wide-ranging scenariosCode0
DPC-Net: Deep Pose Correction for Visual LocalizationCode0
Learning Less is More - 6D Camera Localization via 3D Surface RegressionCode0
InLoc: Indoor Visual Localization with Dense Matching and View SynthesisCode0
Indoor Visual Positioning Aided by CNN-Based Image Retrieval: Training-Free, 3D Modeling-FreeCode0
Illumination-insensitive Binary Descriptor for Visual Measurement Based on Local Inter-patch InvarianceCode0
Show:102550
← PrevPage 15 of 17Next →

Benchmark Results

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