search

initialneil / SplattingAvatar

[CVPR2024] Official implementation of SplattingAvatar.
Other
336 stars 32 forks source link

readme

[CVPR2024] SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

Paper | Video Youtube | Project Page

Official Repository for CVPR 2024 paper SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting.

Lifted optimization

The embedding points of 3DGS on the triangle mesh are updated by the walking on triangle scheme. See the phongsurface module implemented in c++ and pybind11.

Getting Started

pytorch 1.13.1+cu117 is tested

pip install torch==1.13.1 torchvision torchaudio functorch --extra-index-url https://download.pytorch.org/whl/cu117

pytorch3d

git clone https://github.com/facebookresearch/pytorch3d.git cd pytorch3d pip install -e .

install other dependencies

pip install tqdm omegaconf opencv-python libigl pip install trimesh plyfile imageio chumpy lpips pip install packaging pybind11 pip install numpy==1.23.1


- Clone this repo *recursively*. Install Gaussian Splatting's submodules.

git clone --recursive https://github.com/initialneil/SplattingAvatar.git cd SplattingAvatar

cd submodules/diff-gaussian-rasterization pip install .

cd ../submodules/simple-knn pip install .

cd ..


- Install `simple_phongsurf` for *walking on triangles*.

cd model/simple_phongsurf pip install -e .


- Download [FLAME model](https://flame.is.tue.mpg.de/download.php), choose **FLAME 2020** and unzip it, copy 'generic_model.pkl' into `./model/imavatar/FLAME2020`,

- Download [SMPL model](https://smpl.is.tue.mpg.de/download.php) (1.0.0 for Python 2.7 (10 shape PCs)) and move them to the corresponding places:

mv /path/to/smpl/models/basicModel_f_lbs_10_207_0_v1.0.0.pkl model/smplx_utils/smplx_models/smpl/SMPL_FEMALE.pkl mv /path/to/smpl/models/basicmodel_m_lbs_10_207_0_v1.0.0.pkl model/smplx_utils/smplx_models/smpl/SMPL_MALE.pkl


## Preparing dataset
We provide the preprocessed data of the 10 subjects used in the paper.
- Our preprocessing followed [IMavatar](https://github.com/zhengyuf/IMavatar/tree/main/preprocess#preprocess) and replaced the *Segmentation* with [RobustVideoMatting](https://github.com/PeterL1n/RobustVideoMatting).
- Pre-trained checkpoints are provided together with the data.
- [Google Drive](https://drive.google.com/drive/folders/1YPEG1IYgkZWTlibRZfMjhXFMw58JJVeq?usp=sharing) or [Baidu Disk](https://pan.baidu.com/s/12ycpotyE4KUZ-HvhpCcVxw?pwd=bkfh)

<img src="https://github.com/initialneil/SplattingAvatar/raw/master/assets/SplattingAvatar-dataset.jpg" width="800"/> 

## Training

python train_splatting_avatar.py --config configs/splatting_avatar.yaml --dat_dir <path/to/subject>

for example:

python train_splatting_avatar.py --config configs/splatting_avatar.yaml --dat_dir /path-to/bala

you may specify gpu id by adding CUDA_VISIBLE_DEVICES=x before calling python:

CUDA_VISIBLE_DEVICES=0 python train_splatting_avatar.py ...

to disable network_gui, set ip to 'none'

CUDA_VISIBLE_DEVICES=0 python train_splatting_avatar.py ... --ip none

use SIBR_remoteGaussian_app.exe from 3DGS to watch the training

SIBR_remoteGaussian_app.exe --path <path/to/output_of_any_standard_3dgs>

is generated by running the original 3dgs on any original dataset

SIBR_remoteGaussian_app.exe somehow requires a standard 3dgs output to start

it is recommended to change "FPS" to "Trackball" in the viewer

you don't need to change the "path" everytime

## Evaluation

python eval_splatting_avatar.py --config configs/splatting_avatar.yaml --dat_dir <path/to/model_path>

for example:

python eval_splatting_avatar.py --config configs/splatting_avatar.yaml --dat_dir /path-to/bala/output-splatting/last_checkpoint


## Full-body Avatar
We conducted experiments on [PeopleSnapshot](https://graphics.tu-bs.de/people-snapshot).
- Please download the parameter files (the same with InstantAvatar) from: [Baidu Disk](https://pan.baidu.com/s/1g4lSPAYfwbOadnnEDoWjzg?pwd=5gy5) or [Google Drive](https://drive.google.com/drive/folders/1r-fHq5Q_szFYD_Wz394Dnc5G79nG2WHw?usp=sharing).
- Download 4 sequences from PeopleSnapshot (male/female-3/4-casual) and unzip `images` and `masks` to corresponding folders from above.
- Use `scripts/preprocess_PeopleSnapshot.py` to preprocess the data.
- Training:

override with instant_avatar.yaml for PeopleSnapshot in InstantAvatar's format

python train_splatting_avatar.py --config "configs/splatting_avatar.yaml;configs/instant_avatar.yaml" --dat_dir <path/to/subject>

for example:

python train_splatting_avatar.py --config "configs/splatting_avatar.yaml;configs/instant_avatar.yaml" --dat_dir /path-to/female-3-casual

pretrained checkpoints provided in output-splatting/last_checkpoint can be evaluated by eval_splatting_avatar.py

for example:

python eval_splatting_avatar.py --config "configs/splatting_avatar.yaml;configs/instant_avatar.yaml" --dat_dir /path-to/female-3-casual --pc_dir /path-to/female-3-casual/output-splatting/last_checkpoint/point_cloud/iteration_30000

to animate to noval pose aist_demo.npz

python eval_animate.py --config "configs/splatting_avatar.yaml;configs/instant_avatar.yaml" --dat_dir /path-to/female-3-casual --pc_dir /path-to/female-3-casual/output-splatting/last_checkpoint/point_cloud/iteration_30000 --anim_fn /path-to/aist_demo.npz


## GPU requirement
We conducted our experiments on a single NVIDIA RTX 3090 with 24GB.
Training with less GPU memory can be achieved by setting a maximum number of Gaussians.

in configs/splatting_avatar.yaml

model: max_n_gauss: 300000 # or less as needed

or set by command line

python train_splatting_avatar.py --config configs/splatting_avatar.yaml --dat_dir <path/to/subject> model.max_n_gauss=300000


## Citation
If you find our code or paper useful, please cite as:

@inproceedings{SplattingAvatar:CVPR2024, title = {{SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting}}, author = {Shao, Zhijing and Wang, Zhaolong and Li, Zhuang and Wang, Duotun and Lin, Xiangru and Zhang, Yu and Fan, Mingming and Wang, Zeyu}, booktitle = {Computer Vision and Pattern Recognition (CVPR)}, year = {2024} }



## Acknowledgement
We thank the following authors for their excellent works!
- [instant-nsr-pl](https://github.com/bennyguo/instant-nsr-pl)
- [Gaussian Splatting](https://github.com/graphdeco-inria/gaussian-splatting)
- [IMavatar](https://github.com/zhengyuf/IMavatar)
- [INSTA](https://github.com/Zielon/INSTA)

## License
SplattingAvatar
<br>
The code is released under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode) for Noncommercial use only. Any commercial use should get formal permission first.

[Gaussian Splatting](https://github.com/graphdeco-inria/gaussian-splatting/blob/main/LICENSE.md)
<br>
**Inria** and **the Max Planck Institut for Informatik (MPII)** hold all the ownership rights on the *Software* named **gaussian-splatting**. The *Software* is in the process of being registered with the Agence pour la Protection des Programmes (APP).