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

Showing 2650 of 408 papers

TitleStatusHype
From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment LayersCode1
Event-Based Visual Odometry on Non-Holonomic Ground VehiclesCode1
Amirkabir campus dataset: Real-world challenges and scenarios of Visual Inertial Odometry (VIO) for visually impaired peopleCode1
Deep Event Visual OdometryCode1
iMatching: Imperative Correspondence LearningCode1
Converting Depth Images and Point Clouds for Feature-based Pose EstimationCode1
Deep Visual Odometry with Events and FramesCode1
S2LD: Sparse-to-Local-Dense Matching for Geometry-Guided Correspondence EstimationCode1
Transformer-Based Model for Monocular Visual Odometry: A Video Understanding ApproachCode1
Modality-invariant Visual Odometry for Embodied VisionCode1
FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking DatasetsCode1
Dense Prediction Transformer for Scale Estimation in Monocular Visual OdometryCode1
SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and SelectionCode1
ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and LocalizationCode1
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving ScenesCode1
Is Mapping Necessary for Realistic PointGoal Navigation?Code1
LF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative PlaneCode1
360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan EstimationCode1
TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view StereoCode1
MotionHint: Self-Supervised Monocular Visual Odometry with Motion ConstraintsCode1
Towards Robust Monocular Visual Odometry for Flying Robots on Planetary MissionsCode1
Instant Visual Odometry Initialization for Mobile ARCode1
RAM-VO: Less is more in Visual OdometryCode1
VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good EnoughCode1
VOLDOR: Visual Odometry from Log-logistic Dense Optical flow ResidualsCode1
Show:102550
← PrevPage 2 of 17Next →

Benchmark Results

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