search

lzhengning / SubdivNet

Subdivision-based Mesh Convolutional Networks.
MIT License
247 stars 34 forks source link

Questions about input data for segmentation #31

Open whsu2s opened 2 years ago

whsu2s commented 2 years ago

Thanks for sharing the code of your nice work! I've been trying to apply the framework to my own dataset for segmentation. As I understood, the dataroot contains the folders 'train', 'test' and 'raw'. For each sample, there are three files: .obj, .json (labels), and the *.off (in 'raw'). What is unclear to me are:

  1. What are the data in the 'raw' folder? I expect the raw data to be *.obj. What is the purpose of saving the meshes in .off instead of .obj? The remeshing algorithms (MAPS and neural subdivision) have the finest mesh as input and downsample the meshes. However, the meshes in the 'raw' folders have a lower resolution than those in the 'train' and 'test' folders.
  2. How do you obtain the labels (*.json)?

Thank you!

lzhengning commented 2 years ago

Hi, @whsu2s ,

  1. The original datasets (SHREC11, Huambody, etc.) use off formats. The number of faces of remeshed shapes are determined by the subdivision depth and the base size, irrelevant to the resolution of raw meshes.
  2. please refer to #9, #17, #29.