This repository contains the source code of single view reconstruction and of the papers:
-
Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer (TPAMI 2023)
-
SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer (ICCV 2021, Oral)
We follow 3DAttriFlow and evaluate the single view reconstruction quality of SPD on the ShapeNet dataset.
To use our code, make sure that the environment and PyTorch extensions are installed according to the instructions in the main page. Then modify the dataset path in the configuration files.
To train a svr model from scratch, run:
python train_svr.py -c cfgs/SVR.yaml -gpu 0
To evaluate a pre-trained model, first specify the "load_model" path in cfgs/SVR.yaml, then run:
python val_svr.py -c cfgs/SVR.yaml -gpu 0
This repo is based on:
We thank the authors for their great job!