HS-SLAM combines IMU-predicted poses with coarse-to-fine direct refinement to skip descriptor extraction on non-keyframes, gaining 15% tracking speed with comparable accuracy on five EuRoC sequences.
Edge-Assisted Multi-Robot Visual-Inertial SLAM With Efficient Communication,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HS-SLAM: A Fast and Hybrid Strategy-Based SLAM Approach for Low-Speed Autonomous Driving
HS-SLAM combines IMU-predicted poses with coarse-to-fine direct refinement to skip descriptor extraction on non-keyframes, gaining 15% tracking speed with comparable accuracy on five EuRoC sequences.