Search Results for author:
Found 3 papers, 0 papers with code
Feature-based Event Stereo Visual Odometry
We compared our method to the ESVO method, which is the first and still the only stereo event odometry method, showing on par performance on the MVSEC sequences, while on the DSEC dataset ESVO, unlike our method, was unable to handle outdoor driving scenario with default parameters.
Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
Feature-to-feature (F2F) module regresses the future features directly and is therefore able to account for emergent scenery.
Single Level Feature-to-Feature Forecasting with Deformable Convolutions
We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
