PKU-EPIC / MaskClustering

70 stars 2 forks source link

Where can I get the gt_files for ScanNet while not ScanNet++ for evaluation? #1

Closed laliwang closed 4 months ago

laliwang commented 4 months ago

Thanks for your excellent works and generous sharing! Where I notice the data structure of ScanNet in your readme goes as follows: data/scannet/processed

├── scene0011_00 ├── pose <- folder with camera poses │ ├── 0.txt │ ├── 10.txt │ └── ...
├── color <- folder with RGB images │ ├── 0.jpg (or .png/.jpeg) │ ├── 10.jpg (or .png/.jpeg) │ └── ...
├── depth <- folder with depth images │ ├── 0.png (or .jpg/.jpeg) │ ├── 10.png (or .jpg/.jpeg) │ └── ...
├── intrinsic
│ └── intrinsic_depth.txt <- camera intrinsics | └── ... └── scene0011_00_vh_clean_2.ply <- point cloud of the scene └── ... Since I cannot find any files in txt or npz format for evaluation in above path, I just wonder where I can download it? Thanks!

MiYanDoris commented 4 months ago

Sorry for the missing preprocessing script. I've added the script for preparing ScanNet200 ground truth here: preprocess/scannet/prepare_gt.py. It is a simplified version of the original ScanNet toolkit. You can follow the instruction in Readme.md to prepare them. Thanks for your feedback and feel free to contact with me.