Search Results for author:
Found 2 papers, 1 papers with code
DFR: Depth from Rotation by Uncalibrated Image Rectification with Latitudinal Motion Assumption
Despite the increasing prevalence of rotating-style capture (e. g., surveillance cameras), conventional stereo rectification techniques frequently fail due to the rotation-dominant motion and small baseline between views.
Learning Local Features with Context Aggregation for Visual Localization
Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context information.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
