Submitted anonymously.

Submission data

Full name	Depth-SupervisedFeatureMatching
Description	A stereo visual SLAM approach that combines deep feature extraction with geometry-aware matching. The method generates dense depth priors from stereo images and refines feature correspondences using temporal consistency and IMU constraints. A robust pose graph optimization module removes outliers and improves trajectory accuracy in challenging environments with repetitive textures and dynamic objects.
Parameters	Feature points: 2500 Matching confidence threshold: 0.75 Keyframe interval: 8 frames IMU fusion weight: 0.35 Loop closure threshold: 0.82 Bundle adjustment window: 15 keyframes
Programming language(s)	C++, Python
Hardware	A100
Submission creation date	23 Jun, 2026
Last edited	23 Jun, 2026

High-res multi-view results

Low-res many-view results

Low-res two-view results

SLAM results