base on [CVPR 2024] Official repository for "Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians" # Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians ## [Paper](https://arxiv.org/abs/2312.03029) | [Project Page](https://yuelangx.github.io/gaussianheadavatar/) <img src="imgs/teaser.jpg" width="840" height="396"/> ## Requirements * Create a conda environment. ``` conda env create -f environment.yaml ``` * Install [Pytorch3d](https://github.com/facebookresearch/pytorch3d). ``` pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu113_pyt1120/download.html ``` * Install [kaolin](https://github.com/NVIDIAGameWorks/kaolin). ``` pip install kaolin==0.13.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-1.12.0_cu113.html ``` * Install diff-gaussian-rasterization and simple_knn from [gaussian-splatting](https://github.com/graphdeco-inria/gaussian-splatting). Note, for rendering 32-channel images, please modify "NUM_CHANNELS 3" to "NUM_CHANNELS 32" in "diff-gaussian-rasterization/cuda_rasterizer/config.h". ``` cd path/to/gaussian-splatting # Modify "submodules/diff-gaussian-rasterization/cuda_rasterizer/config.h" pip install submodules/diff-gaussian-rasterization pip install submodules/simple-knn ``` * Download ["tets_data.npz"](https://drive.google.com/file/d/1SMkp8v8bDyYxEdyq25jWnAX1zeQuAkNq/view?usp=drive_link) and put it into "assets/". ## Datasets We provide instructions for preprocessing [NeRSemble dataset](https://tobias-kirschstein.github.io/nersemble/): * Apply to download [NeRSemble dataset](https://tobias-kirschstein.github.io/nersemble/) and unzip it into "path/to/raw_NeRSemble/". * Extract the images, cameras and background for specific identities into a structured dataset "NeRSemble/{id}". ``` cd preprocess python preprocess_nersemble.py ``` * Remove background using [BackgroundMattingV2](https://github.com/PeterL1n/BackgroundMattingV2). Please git clone the code. Download [pytorch_resnet101.pth](https://drive.google.com/file/d/1zysR-jW6jydA2zkWfevxD1JpQHglKG1_/view?usp=drive_link) and put it into "path/to/BackgroundMattingV2/assets/". Then run the script we provide "preprocess/remove_background_nersemble.py". ``` cp preprocess/remove_background_nersemble.py path/to/BackgroundMattingV2/ cd path/to/BackgroundMattingV2 python remove_background_nersemble.py ``` * Fit BFM model for head pose and expression coefficients using [Multiview-3DMM-Fitting](https://github.com/YuelangX/Multiview-3DMM-Fitting). Please follow the instructions. We provide a [mini demo dataset](https://drive.google.com/file/d/1OddIml-gJgRQU4YEP-T6USzIQyKSaF7I/view?usp=drive_link) for checking whether the code is runnable. Note, before downloading it, you must first sign the [NeRSemble Terms of Use](https://forms.gle/H4JLdUuehqkBNrBo7). ## Training First, edit the config file, for example "config/train_meshhead_N031", and train the geometry guidance model. ``` python train_meshhead.py --config config/train_meshhead_N031.yaml ``` Second, edit the config file "config/train_gaussianhead_N031", and train the gaussian head avatar. ``` python train_gaussianhead.py --config config/train_gaussianhead_N031.yaml ``` ## Reenactment Once the two-stage training is completed, the trained avatar can be reenacted by a sequence of expression coefficients. Please specify the avatar checkpoints and the source data in the config file "config/reenactment_N031.py" and run the reenactment application. ``` python reenactment.py --config config/reenactment_N031.yaml ``` ## Acknowledgement Part of the code is borrowed from [gaussian-splatting](https://github.com/graphdeco-inria/gaussian-splatting). ## Citation ``` @inproceedings{xu2023gaussianheadavatar, title={Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians}, author={Xu, Yuelang and Chen, Benwang and Li, Zhe and Zhang, Hongwen and Wang, Lizhen and Zheng, Zerong and Liu, Yebin}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2024} } ", Assign "at most 3 tags" to the expected json: {"id":"9083","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"