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 301–350 of 402 papers

TitleStatusHype
End-to-end learning of keypoint detection and matching for relative pose estimation—0
CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization—0
Grad-CAM guided channel-spatial attention module for fine-grained visual classification—0
Appearance-Invariant 6-DoF Visual Localization using Generative Adversarial Networks—0
Do We Really Need Scene-specific Pose Encoders?—0
Learning to Localize in New Environments from Synthetic Training DataCode0
Improving the generalization of network based relative pose regression: dimension reduction as a regularizer—0
Ego-Motion Alignment from Face Detections for Collaborative Augmented Reality—0
Can You Trust Your Pose? Confidence Estimation in Visual Localization—0
Leveraging Local and Global Descriptors in Parallel to Search Correspondences for Visual Localization—0
Domain Adaptation of Learned Features for Visual Localization—0
Image Stylization for Robust Features—0
Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze—0
IF-Net: An Illumination-invariant Feature Network—0
Privacy Preserving Structure-from-Motion—0
Wearable camera-based human absolute localization in large warehouses—0
Adversarial Transfer of Pose Estimation Regression—0
Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings—0
Learning Multi-View Camera Relocalization With Graph Neural Networks—0
Learning Local Features with Context Aggregation for Visual Localization—0
Visual Localization Using Semantic Segmentation and Depth Prediction—0
Dense Semantic 3D Map Based Long-Term Visual Localization with Hybrid Features—0
Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization—0
Semantic Signatures for Large-scale Visual Localization—0
DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving—0
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC—0
A Robust Stereo Camera Localization Method with Prior LiDAR Map Constrains—0
Visual-Inertial Localization for Skid-Steering Robots with Kinematic Constraints—0
Improved Visual Localization via Graph Smoothing—0
Self-supervised Moving Vehicle Tracking with Stereo Sound—0
A Hybrid Compact Neural Architecture for Visual Place RecognitionCode0
Coarse-To-Fine Visual Localization Using Semantic Compact Map—0
Learning Navigation by Visual Localization and Trajectory Prediction—0
Global visual localization in LiDAR-maps through shared 2D-3D embedding space—0
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual LocalizationCode0
TagSLAM: Robust SLAM with Fiducial Markers—0
Hierarchical Encoding of Sequential Data With Compact and Sub-Linear Storage CostCode0
Prior Guided Dropout for Robust Visual Localization in Dynamic EnvironmentsCode0
Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing EnvironmentsCode0
Visual Measurement Integrity Monitoring for UAV Localization—0
Hierarchical Scene Coordinate Classification and Regression for Visual Localization—0
AtLoc: Attention Guided Camera LocalizationCode0
Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual LocalizationCode0
Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization—0
Expert Sample Consensus Applied to Camera Re-LocalizationCode0
To Learn or Not to Learn: Visual Localization from Essential Matrices—0
Sparse-to-Dense Hypercolumn Matching for Long-Term Visual LocalizationCode0
Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environmentCode0
Place recognition in gardens by learning visual representations: data set and benchmark analysis—0
BTEL: A Binary Tree Encoding Approach for Visual Localization—0
Show:102550
← PrevPage 7 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