This is the working code for WACV 2025(Oral) paper 3D Shape Completion using Multi-resolution Spectral Encoding.
conda env create -f environment.yaml
conda activate MSSC
Download the processed datasets and the priors from PatchComplete.
- Train for patches
R=4,R=8, andR=32on ShapeNet dataset.
sh train_script_patch.sh
- Train multi-resolution on ShapeNet.
sh train_script_multi.sh
- Fine-tune on ScanNet dataset
sh train_script_fine.sh
- Generation -
sh generation_script.sh
- Evaluation -
cd evaluation
sh evaluation_script.sh
Please cite us using the following if you found our work useful -
@InProceedings{Deka_2025_WACV,
author = {Deka, Pallabjyoti and Bhattacharya, Saumik and Sen, Debashis and Biswas, Prabir Kumar},
title = {3D Shape Completion using Multi-Resolution Spectral Encoding},
booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)},
month = {February},
year = {2025},
pages = {54-63}
}