Lei Li · Songyou Peng · Zehao Yu · Shaohui Liu · Rémi Pautrat
Xiaochuan Yin · Marc Pollefeys

EMAP enables 3D edge reconstruction from multi-view 2D edge maps.

git clone https://github.com/cvg/EMAP.git
cd EMAP

conda create -n emap python=3.8
conda activate emap

conda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia
pip install -r requirements.txt

Download datasets:

python scripts/download_data.py 

The data is organized as follows:

<scan_id>
|-- meta_data.json      # camera parameters
|-- color               # images for each view
    |-- 0_colors.png
    |-- 1_colors.png
    ...
|-- edge_DexiNed        # edge maps extracted from DexiNed
    |-- 0_colors.png
    |-- 1_colors.png
    ...
|-- edge_PidiNet        # edge maps extracted from PidiNet
    |-- 0_colors.png
    |-- 1_colors.png
    ...

To train and extract edges on different datasets, use the following commands:

bash scripts/run_ABC.bash

bash scripts/run_Replica.bash

bash scripts/run_DTU.bash

We have uploaded the model checkpoints on Google Drive.

To evaluate extracted edges on ABC-NEF_Edge dataset, use the following commands:

python src/eval/eval_ABC.py

• Training Code
• Inference Code
• Evaluation Code
• Custom Dataset Support

Shield:

The majority of EMAP is licensed under a MIT License.

If you find the code useful, please consider the following BibTeX entry.

@InProceedings{li2024neural,
  title={3D Neural Edge Reconstruction},
  author={Li, Lei and Peng, Songyou and Yu, Zehao and Liu, Shaohui and Pautrat, R{\'e}mi and Yin, Xiaochuan and Pollefeys, Marc},
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2024},
}

If you encounter any issues, you can also contact Lei through lllei.li0386@gmail.com.

This project is built upon NeuralUDF, NeuS and MeshUDF. We use pretrained DexiNed and PidiNet for edge map extraction. We thank all the authors for their great work and repos.