At train-time, we embed each pixel of the ground truth image SI as the mean of predefined guide functions f over instance pixels it belongs to, resuling in embeddings e(S, Ψ). We then train the ...
InstaDrive, proposed by SJTU researchers, addresses autonomous driving’s tedious annotation and long-tail data issues. It projects 3D vehicle bounding boxes and BEV map elements into 2D instance ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results