Search Results for author:
Found 3 papers, 0 papers with code
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Further, we propose to use activation maps at different layers of a CNN, as an effective and principled replacement for the multi-resolution image pyramids often used for matching tasks.
Fundamental Matrix Estimation: A Study of Error Criteria
In addition, a new error criterion, Kanatani distance, was proposed and was proved to be the most effective for use during the outlier removal phase from accuracy and efficiency perspectives.
TDT: Teaching Detectors to Track without Fully Annotated Videos
However, their success depends on the availability of videos that are fully annotated with tracking data, which is expensive and hard to obtain.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
