https://github.com/cvg/emap
[CVPR'24] 3D Neural Edge Reconstruction
https://github.com/cvg/emap
3d-reconstruction curves edges lines nerf neural-fields neural-implicit-representations
Last synced: about 1 year ago
JSON representation
[CVPR'24] 3D Neural Edge Reconstruction
- Host: GitHub
- URL: https://github.com/cvg/emap
- Owner: cvg
- License: mit
- Created: 2024-05-29T02:51:27.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-09T17:49:03.000Z (almost 2 years ago)
- Last Synced: 2025-04-13T05:13:11.834Z (about 1 year ago)
- Topics: 3d-reconstruction, curves, edges, lines, nerf, neural-fields, neural-implicit-representations
- Language: Python
- Homepage: https://neural-edge-map.github.io/
- Size: 4.78 MB
- Stars: 181
- Watchers: 13
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
3D Neural Edge Reconstruction
Lei Li
·
Songyou Peng
·
Zehao Yu
·
Shaohui Liu
·
Rémi Pautrat
Xiaochuan Yin
·
Marc Pollefeys
CVPR 2024
Paper | Video | Project Page
EMAP enables 3D edge reconstruction from multi-view 2D edge maps.
## Installation
```
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
```
## Datasets
Download datasets:
```
python scripts/download_data.py
```
The data is organized as follows:
```
|-- 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
...
```
## Training and Edge Extraction
To train and extract edges on different datasets, use the following commands:
#### ABC-NEF_Edge Dataset
```
bash scripts/run_ABC.bash
```
#### Replica_Edge Dataset
```
bash scripts/run_Replica.bash
```
#### DTU_Edge Dataset
```
bash scripts/run_DTU.bash
```
### Checkpoints
We have uploaded the model checkpoints on [Google Drive](https://drive.google.com/file/d/1kU87MqDv5IvwjCt8I8KecTlIok39fuws/view?usp=sharing).
## Evaluation
To evaluate extracted edges on ABC-NEF_Edge dataset, use the following commands:
#### ABC-NEF_Edge Dataset
```
python src/eval/eval_ABC.py
```
## Code Release Status
- [x] Training Code
- [x] Inference Code
- [x] Evaluation Code
- [ ] Custom Dataset Support
## License
Shield: [](https://opensource.org/licenses/MIT)
The majority of EMAP is licensed under a [MIT License](LICENSE.txt).
If you find the code useful, please consider the following BibTeX entry.
```BibTeX
@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},
}
```
## Contact
If you encounter any issues, you can also contact Lei through lllei.li0386@gmail.com.
## Acknowledgement
This project is built upon [NeuralUDF](https://github.com/xxlong0/NeuralUDF), [NeuS](https://github.com/Totoro97/NeuS) and [MeshUDF](https://github.com/cvlab-epfl/MeshUDF). We use pretrained [DexiNed](https://github.com/xavysp/DexiNed) and [PidiNet](https://github.com/hellozhuo/pidinet) for edge map extraction. We thank all the authors for their great work and repos.