https://github.com/ollieboyne/found
Official code for FOUND: Foot Optimisation with Uncertain Normals for Surface Deformation using Synthetic Data
https://github.com/ollieboyne/found
3d-reconstruction computer-vision surface-normals surface-normals-estimation surface-reconstruction
Last synced: 9 months ago
JSON representation
Official code for FOUND: Foot Optimisation with Uncertain Normals for Surface Deformation using Synthetic Data
- Host: GitHub
- URL: https://github.com/ollieboyne/found
- Owner: OllieBoyne
- License: mit
- Created: 2023-10-24T11:46:42.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-02-12T18:07:07.000Z (over 1 year ago)
- Last Synced: 2025-02-12T19:24:39.097Z (over 1 year ago)
- Topics: 3d-reconstruction, computer-vision, surface-normals, surface-normals-estimation, surface-reconstruction
- Language: Python
- Homepage: http://www.ollieboyne.com/FOUND/
- Size: 27.4 MB
- Stars: 51
- Watchers: 3
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
This repository contains the code for 3D shape fitting to predicted surface normals, as shown in our paper:
> **FOUND: Foot Optimisation with Uncertain Normals for Surface Deformation using Synthetic Data** \
> Winter Conference on Applications of Computer Vision 2024 \
> [Oliver Boyne](https://ollieboyne.github.io), [Gwangbin Bae](https://www.baegwangbin.com/), [James Charles](http://www.jjcvision.com), and [Roberto Cipolla](https://mi.eng.cam.ac.uk/~cipolla/) \
> [[arXiv]](https://arxiv.org/abs/2310.18279) [[project page]](https://ollieboyne.github.io/FOUND/)
**[Feb 2025]** Check out our new work on recovering the FIND model from images using dense correspondences! [[FOCUS]](https://www.ollieboyne.com/FOCUS)
## Quickstart
1) `git clone --recurse-submodules http://github.com/OllieBoyne/FOUND`
2) Install dependencies: `pip install -r requirements.txt`
3) Download the [pretrained FIND model](https://drive.google.com/drive/folders/1XWmEVo3AdnhJU2fs6igls-emp93beQpm?usp=share_link) to `data/find_nfap`
4) Download our [benchmark foot dataset](https://github.com/OllieBoyne/Foot3D) to `data/scans`
5) Fit a single scan:
```
python FOUND/fit.py --exp_name --data_folder
```
You can use `--cfg .yaml` to use a config file to set parameters. See [`args.py`](utils/args.py) for all arguments, and [`example-cfg.yaml`](example-cfg.yaml) for an example config file.
6) Evaluate all of our reconstruction dataset:
```
python FOUND/eval.py --data_folder --gpus
```
gpu_indices is a space separated list, e.g. `--gpus 0 1 2 3`
## Data
We provide our synthetic foot dataset, [SynFoot](https://github.com/OllieBoyne/SynFoot), which contains 50K synthetic foot scans, with RGB, normals, and masks.
We also provide a benchmark multiview evaluative dataset, [Foot3D](https://github.com/OllieBoyne/Foot3D).
### Related work
Please check out all of our projects that built into this work!
- [FIND - Generative foot model](https://ollieboyne.github.io/FIND)
- [Surface Normal Estimation w/ Uncertainty](https://github.com/baegwangbin/surface_normal_uncertainty)
- [BlenderSynth - Synthetic data generation](https://ollieboyne.github.io/BlenderSynth)
### Citation
If you use our work, please cite:
```
@inproceedings{boyne2024found,
title={FOUND: {F}oot {O}ptimisation with {U}ncertain {N}ormals for Surface {D}eformation using Synthetic Data},
author={Boyne, Oliver and Bae, Gwangbin and Charles, James and Cipolla, Roberto},
booktitle={Winter Conference on Applications of Computer Vision (WACV)},
year={2024}
}
```
### Troubleshooting
If you have any issues with `trimesh` and `shapely`, see [misc/shapely.md](misc/shapely.md).