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 1–50 of 408 papers

TitleStatusHype
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual OdometryCode7
pySLAM: An Open-Source, Modular, and Extensible Framework for SLAMCode7
Deep Patch Visual SLAMCode4
Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual OdometryCode4
LEAP-VO: Long-term Effective Any Point Tracking for Visual OdometryCode3
Reinforcement Learning Meets Visual OdometryCode3
MUSt3R: Multi-view Network for Stereo 3D ReconstructionCode3
Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized MappingCode2
SiLK -- Simple Learned KeypointsCode2
ESVO2: Direct Visual-Inertial Odometry with Stereo Event CamerasCode2
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic EnvironmentsCode2
VOLoc: Visual Place Recognition by Querying Compressed Lidar MapCode2
PVO: Panoptic Visual OdometryCode2
SR-LIVO: LiDAR-Inertial-Visual Odometry and Mapping with Sweep ReconstructionCode2
IMU-Aided Event-based Stereo Visual OdometryCode2
VBR: A Vision Benchmark in RomeCode2
YOLOPoint Joint Keypoint and Object DetectionCode2
Deep Patch Visual OdometryCode2
LIR-LIVO: A Lightweight,Robust LiDAR/Vision/Inertial Odometry with Illumination-Resilient Deep FeaturesCode2
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motionCode2
Multi-Session SLAM with Differentiable Wide-Baseline Pose OptimizationCode2
IncEventGS: Pose-Free Gaussian Splatting from a Single Event CameraCode2
EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearnerCode1
FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking DatasetsCode1
RAM-VO: Less is more in Visual OdometryCode1
ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D CamerasCode1
OV^2SLAM : A Fully Online and Versatile Visual SLAM for Real-Time ApplicationsCode1
Feature-metric Loss for Self-supervised Learning of Depth and EgomotionCode1
From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment LayersCode1
Event-based Stereo Visual OdometryCode1
Deep Visual Odometry with Events and FramesCode1
360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan EstimationCode1
ES-PTAM: Event-based Stereo Parallel Tracking and MappingCode1
Event-Based Visual Odometry on Non-Holonomic Ground VehiclesCode1
MotionHint: Self-Supervised Monocular Visual Odometry with Motion ConstraintsCode1
Amirkabir campus dataset: Real-world challenges and scenarios of Visual Inertial Odometry (VIO) for visually impaired peopleCode1
Modality-invariant Visual Odometry for Embodied VisionCode1
Visual Odometry Revisited: What Should Be Learnt?Code1
LGU-SLAM: Learnable Gaussian Uncertainty Matching with Deformable Correlation Sampling for Deep Visual SLAMCode1
DF-VO: What Should Be Learnt for Visual Odometry?Code1
ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and LocalizationCode1
LF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative PlaneCode1
Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement LearningCode1
Nonparametric Continuous Sensor RegistrationCode1
Instant Visual Odometry Initialization for Mobile ARCode1
Is Mapping Necessary for Realistic PointGoal Navigation?Code1
Deep Event Visual OdometryCode1
Deep Keypoint-Based Camera Pose Estimation with Geometric ConstraintsCode1
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving ScenesCode1
Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAMCode1
Show:102550
← PrevPage 1 of 9Next →

Benchmark Results

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