{"id":14529285,"url":"https://github.com/snap-research/unsupervised-volumetric-animation","last_synced_at":"2025-04-14T00:22:56.583Z","repository":{"id":73822896,"uuid":"593373065","full_name":"snap-research/unsupervised-volumetric-animation","owner":"snap-research","description":"The repository for paper Unsupervised Volumetric Animation","archived":false,"fork":false,"pushed_at":"2023-09-22T16:57:12.000Z","size":95407,"stargazers_count":69,"open_issues_count":4,"forks_count":1,"subscribers_count":25,"default_branch":"main","last_synced_at":"2025-03-27T14:22:01.004Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/snap-research.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-01-25T21:07:34.000Z","updated_at":"2024-11-15T21:32:08.000Z","dependencies_parsed_at":"2024-11-15T21:33:17.757Z","dependency_job_id":null,"html_url":"https://github.com/snap-research/unsupervised-volumetric-animation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2Funsupervised-volumetric-animation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2Funsupervised-volumetric-animation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2Funsupervised-volumetric-animation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/snap-research%2Funsupervised-volumetric-animation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/snap-research","download_url":"https://codeload.github.com/snap-research/unsupervised-volumetric-animation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248800072,"owners_count":21163404,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-09-05T00:00:58.408Z","updated_at":"2025-04-14T00:22:56.572Z","avatar_url":"https://github.com/snap-research.png","language":"Python","funding_links":[],"categories":["Researchers and labs"],"sub_categories":[],"readme":"# Unsupervised Volumetric Animation\n\nThis repository contains the source code for the CVPR'2023 paper [Unsupervised Volumetric Animation](https://arxiv.org/abs/2301.11326).\nFor more qualitiative examples visit our [project page](https://snap-research.github.io/unsupervised-volumetric-animation/).\n\nHere is an example of several images produced by our method. \nOn the left is sample visualization: In the first column the driving video is shown. For the remaining columns the top image is animated by using motions extracted from the driving.\nOn the right is rotation visualization: We show source image as well as rotated rgb, depth, normals and segments. \n\nSample animation           |  Rotation visualization\n:-------------------------:|:-------------------------:\n![](./assets/sample.gif)  |  ![](./assets/rotation.gif)\n\n### Installation\n\nWe support ```python3```. To install the dependencies run:\n```bash\npip install -r requirements.txt\n```\n\n### YAML configs\n\nThere are several configuration files one for each `dataset` in the `config` folder named as ```config/dataset_name_stage.yaml```. We adjust the configuration to run on 8 A100 GPU.\n\n### Pre-trained checkpoints\nCheckpoints can be found under this [link](https://drive.google.com/drive/folders/1RKbzSRRQvJ0bsEMDq1ed9Fk3x8Pw-clE?usp=sharing).\n\n### Inversion\nInversion, to run inversion on your own image use:\n```bash\npython inversion.py  --config config/dataset_name.yaml --driving_video path/to/driving --source_image path/to/source --checkpoint tb-logs/vox_second_stage/{time}/checkpoints/last.cpkt\n```\nThe result can be seen with tensorboard.\n\n\n### Training\n\nTo train a model, fist, download the mraa checkpoints and place them into ```./```.\nThen run the following commands:\n\n```bash\npython train.py --config config/vox_first_stage.yaml\n# [Optional] To save time one could first train with 128 resolution:\npython train.py --config config/vox_second_stage_128.yaml --checkpoint tb-logs/vox_first_stage/{time}/checkpoints/last.cpkt\npython train.py --config config/vox_second_stage.yaml --checkpoint tb-logs/vox_first_stage/{time}/checkpoints/last.cpkt\n```\n\nCitation:\n```\n@article{siarohin2023unsupervised,\n    author  = {Siarohin, Aliaksandr and Menapace, Willi and Skorokhodov, Ivan and Olszewski, Kyle and Lee, Hsin-Ying and Ren, Jian and  Chai, Menglei and Tulyakov, Sergey},\n    title   = {Unsupervised Volumetric Animation},\n    journal = {arXiv preprint arXiv:2301.11326},\n    year    = {2023},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnap-research%2Funsupervised-volumetric-animation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsnap-research%2Funsupervised-volumetric-animation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsnap-research%2Funsupervised-volumetric-animation/lists"}