Search Results for author: Spondon Kundu

Found 1 papers, 1 papers with code

ViewSynth: Learning Local Features from Depth using View Synthesis

1 code implementation22 Nov 2019 Jisan Mahmud, Rajat Vikram Singh, Peri Akiva, Spondon Kundu, Kuan-Chuan Peng, Jan-Michael Frahm

By learning view synthesis, we explicitly encourage the feature extractor to encode information about not only the visible, but also the occluded parts of the scene.

Camera Localization Keypoint Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.