292-reconstructing-personalized-semantic-facial-nerf-models-from-monocular-video
Science Score: 18.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (2.3%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
·
Repository
Basic Info
- Host: GitHub
- Owner: SZU-AdvTech-2023
- Language: Python
- Default Branch: main
- Size: 2.37 MB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Created over 2 years ago
· Last pushed over 2 years ago
Metadata Files
Citation
https://github.com/SZU-AdvTech-2023/292-Reconstructing-Personalized-Semantic-Facial-NeRF-Models-From-Monocular-Video/blob/main/
# NeRF
##
GPURTX 3090.
Install requirements.txt:
```
pip install -r requirements.txt
```
Install [PyTorch](https://pytorch.org/get-started/locally/).
Install [tiny-cuda-nn](https://github.com/NVlabs/tiny-cuda-nn)
```
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
```
##
[preprocessed dataset](https://drive.google.com/drive/folders/1OiUvo7vHekVpy67Nuxnh3EuJQo7hlSq1?usp=sharing)./dataset
```
dataset
id1
head_imgs #
ori_imgs #
parsing #
transforms.json #
bc.jpg #
id2
...
...
```
`run_train.sh` NeRFBlendShape
```
bash run_train.sh id1 -500 0
```
`id1`500GPU_ID`0`
`run.sh``get_max.py``max_46.txt``min_46.txt``dataset/$NAME``run_nerfblendshape.py``run_nerfblendshape.py`
`--workspace`
`--basis_num`46
`--use_lpips`
`--add_mean`'1.0'
##
checkpoints`the_name_of_workspace/checkpoints`.
to run inference with a given checkpoint:
```
bash run_infer.sh id1 -500 0 the_path_of_your_checkpoint
```
`id1``the_path_of_your_checkpoint`500GPU_ID`0`
`generate_video.py`
Owner
- Name: SZU-AdvTech-2023
- Login: SZU-AdvTech-2023
- Kind: organization
- Repositories: 1
- Profile: https://github.com/SZU-AdvTech-2023
Citation (citation.txt)
@article{REPO292,
author = "Gao, Xuan and Zhong, Chenglai and Xiang, Jun and Hong, Yang and Guo, Yudong and Zhang, Juyong",
journal = "ACM Transactions on Graphics (TOG)",
number = "6",
pages = "1--12",
title = "{Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video}",
volume = "41",
year = "2022"
}