Submitted anonymously.

Submission data

Full nameAdaptiveHybridVisualOdometry
DescriptionA hybrid visual odometry system that combines direct image alignment with sparse feature tracking. The method dynamically switches between tracking modes based on scene texture and motion characteristics. Stereo depth and IMU measurements are fused through an adaptive Kalman filter, while loop closure detection reduces long-term drift and improves global consistency.
ParametersMaximum tracked features: 3000
Direct alignment pyramid levels: 4
Feature re-detection interval: 10 frames
IMU update rate: 200 Hz
Loop closure similarity threshold: 0.85
Pose optimization iterations: 50
Programming language(s)C++, Python, CUDA
HardwareA100
Submission creation date23 Jun, 2026
Last edited23 Jun, 2026

High-res multi-view results



Infoallhigh-res
multi-view
indooroutdoorcourty.delive.electrofacadekickermeadowofficepipesplaygr.reliefrelief.terraceterrai.
No results yet.

Low-res many-view results



Infoalllow-res
many-view
indooroutdoorlakesidesand boxstorage roomstorage room 2tunnel
No results yet.

Low-res two-view results



Infoalldeliv. area 1ldeliv. area 1sdeliv. area 2ldeliv. area 2sdeliv. area 3ldeliv. area 3select. 1lelect. 1select. 2lelect. 2select. 3lelect. 3sfacade 1sforest 1sforest 2splayg. 1lplayg. 1splayg. 2lplayg. 2splayg. 3lplayg. 3sterra. 1sterra. 2sterra. 1lterra. 1sterra. 2lterra. 2s
No results yet.

SLAM results



allboxesboxes darkbuddhacables 4cables 5desk 1desk 2desk changing 2desk dark 1desk dark 2desk global light changesdesk ir lightdinodroneforeground occlusionhelmetkidnap 2lamplarge loop 2large loop 3large non loopmotion 2motion 3motion 4planar 1reflective 2scale changetable 1table 2table 5table 6table global light changestable local light changestable scenetrashbin
MethodInfo
No results yet.