no code implementations • 30 Sep 2019 • Zhenzhen Xiang, Jingrui Yu, Jie Li, Jianbo Su
As for the pose tracker, we propose a visual odometry system fusing both the feature matching and the virtual LiDAR scan matching results.
1 code implementation • 16 Sep 2019 • Zhenzhen Xiang, Anbo Bao, Jie Li, Jianbo Su
On the other hand, feature fusion modules are designed to combine different modal of semantic features, which leverage the information from both inputs for better accuracy.