search

PRBonn / deep-point-map-compression

MIT License
95 stars 28 forks source link

Have you tried add the symmetric plane distance to the loss #14

Closed ZorAttC closed 6 months ago

ZorAttC commented 6 months ago

As I can see the upsamlping result of the encoded pointcloud is somehow noisy，e.g. the ground points should be lying on the ground neatly but actually it shifts a lot and seems noisy.I want to know have you guys tried to add the the symmetric plane distance to the loss? (it seems that it will help these points to lie on the same ground)

louis-wiesmann commented 6 months ago

Hey @ZorAttC, yes I agree that this could improve the network quite a bit. Probably even precomputing the normals and adding them could already help. We didn't do it since we did not want to be reliable on the normal computation.

ZorAttC commented 6 months ago

haha,is computing the normals a heavy burden?it doesn't involve in the forward stage ,so it may not get the encoder and decoder to get slower.

louis-wiesmann commented 6 months ago

I agree 100% . In comparison to run a convolutional neural network its no effort at all. And nowadays I would probably also go for it.

ZorAttC commented 6 months ago

@louis-wiesmann Thx for your immediate reply,it really helps!