Open 571502680 opened 5 years ago
But the paper uses the Semantic Separation Grid of S*S,if i use 2D reprojections of the mesh vertex, and its size is the shape of pictures!
Just use the label of the nearest pixel, to generate a rough segmentation.
Could you share the train.py?
We will release an enhanced version of our method with the training code. (maybe in months)
2D reprojections of the mesh vertex according to the pose can tell you ground truth segmentations.