search

mabaorui / NeuralPull

Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
MIT License
179 stars 28 forks source link

Single View Reconstruction Experiment #13

Closed low5545 closed 2 years ago

low5545 commented 2 years ago

Hi Baorui,

I have some questions regarding this experiment presented in Section 4.2, hope you can help me with this.

  1. Is the L1 CD metric reported in Table 7 multiplied by a constant factor of 0.5, as shown here?
  2. Is there any (additional) normalization applied on the point clouds obtained from the Occupancy Networks ShapeNet dataset for training & evaluation respectively? If not, does that mean the point clouds are bounded within a unit cube centered at 0 with a padding of 0.05 on all sides?
  3. Is it true that only the first view for every object in the dataset is used for evaluation, as done in Occupancy Networks?

Thanks!

mabaorui commented 2 years ago

Hi Yonghui， Metric calculation and dataset preprocessing are both exactly the same with Occupancy Networks.

low5545 commented 2 years ago

Thanks for the info!