search

SimingYan / IAE

[ICCV 2023] "Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning"
98 stars 17 forks source link

Completion results #5

Closed ListIndexOutOfRange closed 2 years ago

ListIndexOutOfRange commented 2 years ago

Hi, thanks for your great work !

I don't quite understand how you obtain the completion results on ScanNet (Figure 4 of your article): as far as I understand, the model outputs implicit function values for ambiant points (that is, points uniformly sampled in the unit cube), so the output is simply one scalar values in [-1, 1] for each ambiant point. But it seems you obtain surfaces. Is that correct ? And if so, how is that done ?

SimingYan commented 2 years ago

Hi @ListIndexOutOfRange,

We used the marching cubes algorithm to extract the mesh completion results. There are many good implementations and I recommand the convolutional occupancy network repo for your reference.