Search Results for author:
Found 2 papers, 0 papers with code
Accurate Visual-Inertial SLAM by Feature Re-identification
We propose a novel feature re-identification method for real-time visual-inertial SLAM.
UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching
Extensive experiments show that the proposed method achieves the highest ground truth covering ratio compared with other cascade cost volume based stereo matching methods.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
