Learning-Deep-Learning

VPN: Cross-view Semantic Segmentation for Sensing Surroundings

September 2020

tl;dr: Generate cross-view segmentation with view parsing network.

Overall impression

The paper could have been written more clearly. Terminology is not well defined and the figure is not clear.

The idea of using semantic segmentation to bridge the sim2real gap is explored in many BEV semantic segmentation tasks such as BEV-Seg, CAM2BEV, VPN.

Key ideas

Technical details

Notes