Search Results for author:
Found 4 papers, 3 papers with code
Uncertainty Driven Active Learning for Image Segmentation in Underwater Inspection
In addition, HyperSeg is trained with a pipeline inspection dataset of over 50, 000 images.
Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry
This paper overviews different pose representations and metric functions in visual odometry (VO) networks.
Monocular visual simultaneous localization and mapping:(r) evolution from geometry to deep learning-based pipelines
With the rise of deep learning, there is a fundamental change in visual simultaneous localization and mapping (SLAM) algorithms toward developing different modules trained as end-to-end pipelines.
Monocular Visual Odometry
Simultaneous Localization and Mapping
UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor
In this work, we introduce an unsupervised deep learning-based interest point detector and descriptor.
