Closed RG2806 closed 1 year ago
Hey, Thanks for open sourcing this awesome work. In your paper, you discuss about using features of object in appearance cost. Can you tell how do you get those features?
Thanks
Extract the instance features from 3D detector backbone. The features are further encoded into a compact vector similar to regular RCNN does.
Hey, Thanks for open sourcing this awesome work. In your paper, you discuss about using features of object in appearance cost. Can you tell how do you get those features?