Visual Odometry
95 papers with code • 0 benchmarks • 21 datasets
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
Benchmarks
These leaderboards are used to track progress in Visual Odometry
Libraries
Use these libraries to find Visual Odometry models and implementationsDatasets
KITTI
TUM RGB-D
Virtual KITTI
TartanAir
Event-Camera Dataset
Virtual KITTI 2
4Seasons
TUM monoVO
EndoSLAM
Latest papers
SiLK -- Simple Learned Keypoints
Keypoint detection & descriptors are foundational tech-nologies for computer vision tasks like image matching, 3D reconstruction and visual odometry.
FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets
The stereo datasets include synchronized stereo images in dynamic underwater environments with objects of known-size.
Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry
Monocular visual odometry consists of the estimation of the position of an agent through images of a single camera, and it is applied in autonomous vehicles, medical robots, and augmented reality.
Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping
A spatial AI that can perform complex tasks through visual signals and cooperate with humans is highly anticipated.
SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection
SF2SE3 then iteratively (1) samples pixel sets to compute SE(3)-motion proposals, and (2) selects the best SE(3)-motion proposal with respect to a maximum coverage formulation.
DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments
geniussh/dytanvo
•
•
Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments.
Deep Patch Visual Odometry
princeton-vl/dpvo
•
•
NeurIPS 2023
DPVO disproves this assumption, showing that it is possible to get the best accuracy and efficiency by exploiting the advantages of sparse patch-based matching over dense flow.
ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and Localization
We present the ALTO dataset, a vision-focused dataset for the development and benchmarking of Visual Place Recognition and Localization methods for Unmanned Aerial Vehicles.
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
A naive way is to accomplish them independently in a sequential or parallel manner, but there are many drawbacks, i. e., 1) the depth and VO results suffer from the inherent scale ambiguity issue; 2) the BEV layout is directly predicted from the front-view image without using any depth-related information, although the depth map contains useful geometry clues for inferring scene layouts.
Physical Passive Patch Adversarial Attacks on Visual Odometry Systems
While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model's output on a set of inputs.
