SOTAVerified

Visual Odometry

Visual Odometry is an important area of information fusion in which the central aim is to estimate the pose of a robot using data collected by visual sensors.

Source: Bi-objective Optimization for Robust RGB-D Visual Odometry

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 408 papers

TitleStatusHype
Visual Odometry Revisited: What Should Be Learnt?Code1
Feature-metric Loss for Self-supervised Learning of Depth and EgomotionCode1
Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement LearningCode1
iMatching: Imperative Correspondence LearningCode1
Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAMCode1
Instant Visual Odometry Initialization for Mobile ARCode1
Event-based Stereo Visual OdometryCode1
Deep Keypoint-Based Camera Pose Estimation with Geometric ConstraintsCode1
Modality-invariant Visual Odometry for Embodied VisionCode1
Dense Prediction Transformer for Scale Estimation in Monocular Visual OdometryCode1
Show:102550
← PrevPage 5 of 41Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CIVORelative Position Error Translation [cm]1.36—Unverified