hyperpc's Introduction

Hyperspherical Embedding for Point Cloud Completion

[Project Page] [Paper]

This repository contains source code for Hyperspherical Embedding for Point Cloud Completion (CVPR 2023).

Prerequisites

Download the datasets for point cloud completion: ModelNet40, Completion3D, MVP, ShapeNet. Fill in the corresponding data path in run.sh.
Check the docker files in docker/ and build docker image:

cd docker/
./build.sh

Create docker container using one GPU

./run.sh 0

Check the config file cfgs/config.yaml each time you run the experiment.

Training

./train.sh

For multi-task learning: Set the task in cfgs/config.yaml to be a list of the desired tasks. For example, to train on both classification and comletion tasks, set task to be ['classification','completion'].

Evaluation

Keep all the config parameters as training, and set eval to True, and then run:

./train.sh

TensorBoard Visualization

Set the --logdir in tensorboard.sh to be the desired log directory and run:

./tensorboard.sh

Citations

If you find this work useful for your research, please cite HyperPC in your publications.

@InProceedings{Zhang_2023_CVPR,
    author    = {Zhang, Junming and Zhang, Haomeng and Vasudevan, Ram and 
                Johnson-Roberson, Matthew},
    title     = {Hyperspherical Embedding for Point Cloud Completion},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and 
                Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {5323-5332}
}

hyperpc's People

Contributors

Stargazers

Watchers

hyperpc's Issues

Dataset download

Hello,why I can't download the ModelNet40,Completion3D?
I click the link but don't have reaction.
Maybe the dataset I can change my dataset just like MPEG 8i owili ?
Thanks.

NN Architecture not matching input shape

I'm trying to run the code and have the docker image set up. After running train.py, I get this error:

Jitting Chamfer 3D
Loaded JIT 3D CUDA chamfer distance

**************************

	dataset:m40
	task:completion
	bsize:64
	max_epoch:100
	lr:0.0002
	lr_step_size:40
	lr_gamma:0.2
	check_dir:checkpoint_mvp_pc
	log_dir:logs_mvp_pc
	encoder_choice:pcn
	completion_decoder_choice:folding
	maxpool_bottleneck:1024
	use_hyperspherical_module:True
	hyper_bottleneck:512
	use_hyperspherical_encoding:True
	norm_order:2
	hyperspherical_module_layers:1
	hyperspherical_module_BN:False
	weight_sec_loss:None
	mlps_classifier:512,256,16
	use_BN_classifier:True
	mlps_segmentator:512,256,50
	use_BN_segmentator:True
	eval:False
	pretrained_path:None
	compute_gradient_norm:False
	grad_surgey_flag:False
	uncertainty_flag:False
	optimal_search:False
	ratio:0.0001

**************************

Model name: m40_pc_b64ep100lr0.0002s40g0.2_pcn_HyperModuleTrue_HyperEncodeTrue_MaxPool1024-Hyper512-NormOrder2-LayerNum1-HyperModuleBNFalse_folding
Downloading http://modelnet.cs.princeton.edu/ModelNet40.zip
Extracting data_root/ModelNet40/ModelNet40.zip
Processing...
Done!

Start training!

Traceback (most recent call last):
  File "main.py", line 540, in <module>
    train(args=args, train_dataloader=train_dataloader, test_dataloader=test_dataloader)
  File "main.py", line 249, in train
    train_one_epoch(args, train_dataloader, optimizer, logger, epoch, check_dir)
  File "main.py", line 77, in train_one_epoch
    model(None, pos, batch)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/harry/GitRepos/HyperPC/utils/model.py", line 133, in forward
    self.pred_completion = self.decoder_completion(encoding_feature)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/harry/GitRepos/HyperPC/utils/models/decoder_folding.py", line 38, in forward
    x = self.fold1(x)  # x = batch,3,45^2
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/harry/GitRepos/HyperPC/utils/models/decoder_folding.py", line 54, in forward
    x = self.relu(self.conv1(x))  # x = batch,512,45^2
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 302, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 298, in _conv_forward
    return F.conv1d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [512, 1026, 1], expected input[64, 514, 2025] to have 1026 channels, but got 514 channels instead

Any suggestions or sample config files to use?