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 351–375 of 402 papers

TitleStatusHype
Visual Localization by Learning Objects-Of-Interest Dense Match Regression—0
Panoramic Annular Localizer: Tackling the Variation Challenges of Outdoor Localization Using Panoramic Annular Images and Active Deep DescriptorsCode0
Neural-Guided RANSAC: Learning Where to Sample Model HypothesesCode0
Deep Closest Point: Learning Representations for Point Cloud RegistrationCode0
Learning Scene Geometry for Visual Localization in Challenging Conditions—0
Geometric Image Correspondence Verification by Dense Pixel Matching—0
Visual Localization Using Sparse Semantic 3D Map—0
Learning Matchable Image Transformations for Long-term Metric Visual LocalizationCode0
Understanding the Limitations of CNN-based Absolute Camera Pose RegressionCode0
A Generative Map for Image-based Camera LocalizationCode0
SASSE: Scalable and Adaptable 6-DOF Pose Estimation—0
Deep Global-Relative Networks for End-to-End 6-DoF Visual Localization and Odometry—0
Improving Nighttime Retrieval-Based Localization—0
From Coarse to Fine: Robust Hierarchical Localization at Large ScaleCode0
Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization—0
Visual Localization Under Appearance Change: Filtering ApproachesCode0
Neighbourhood Consensus NetworksCode0
Visual Localization of Key Positions for Visually Impaired People—0
Night-to-Day Image Translation for Retrieval-based LocalizationCode0
Leveraging Deep Visual Descriptors for Hierarchical Efficient LocalizationCode0
Semantic Match Consistency for Long-Term Visual Localization—0
Connecting Visual Experiences using Max-flow Network with Application to Visual Localization—0
Hybrid Scene Compression for Visual Localization—0
Dynamic Objects Segmentation for Visual Localization in Urban Environments—0
Learning models for visual 3D localization with implicit mapping—0
Show:102550
← PrevPage 15 of 17Next →
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