planarreconstruction's Introduction

PlanarReconstruction

PyTorch implementation of our CVPR 2019 paper:

Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding

Zehao Yu*, Jia Zheng*, Dongze Lian, Zihan Zhou, Shenghua Gao

(* Equal Contribution)

Prepare data

Please download the .tfrecords files for training and testing converted by Chen Liu from here. Then convert the .tfrecords to .npz files as the following:

python data_tools/convert_tfrecords.py --data_type=train --input_tfrecords_file=*train.tfrecords --output_dir=/path/to/save/processd/data
python data_tools/convert_tfrecords.py --data_type=val --input_tfrecords_file=*val.tfrecords --output_dir=/path/to/save/processd/data

Train

Run the following command to train our network.

python main.py train with dataset.root_dir=/path/to/save/processd/data

Evaluation

Please download our trained network from here.

To evaluate the performance of our method, please run:

python main.py eval with dataset.root_dir=/path/to/save/processd/data resume_dir=pretrained.pt dataset.batch_size=1

Prediction

Run the following command to predict on a single image.

python predict.py eval with resume_dir=pretrained.pt input_image=/path/to/image

Acknowledgements

We thank Chen Liu for his great works and repos.

Citation

Please cite our paper for any purpose of usage.

@inproceedings{Yu2019Single,
  title={Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding},
  author={Zehao Yu and Jia Zheng and Dongze Lian and Zihan Zhou and Shenghua Gao},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2019}
}

Recommend Projects