{"id":13467298,"url":"https://github.com/iPERDance/iPERCore","last_synced_at":"2025-03-26T01:30:45.648Z","repository":{"id":37717239,"uuid":"313664064","full_name":"iPERDance/iPERCore","owner":"iPERDance","description":"Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis","archived":false,"fork":false,"pushed_at":"2023-05-12T03:23:38.000Z","size":23570,"stargazers_count":2415,"open_issues_count":72,"forks_count":312,"subscribers_count":50,"default_branch":"main","last_synced_at":"2025-03-17T09:26:00.203Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://iperdance.github.io/work/impersonator-plus-plus.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iPERDance.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2020-11-17T15:36:25.000Z","updated_at":"2025-03-15T02:10:33.000Z","dependencies_parsed_at":"2024-01-18T20:24:44.899Z","dependency_job_id":null,"html_url":"https://github.com/iPERDance/iPERCore","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/iPERDance%2FiPERCore","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iPERDance%2FiPERCore/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iPERDance%2FiPERCore/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iPERDance%2FiPERCore/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iPERDance","download_url":"https://codeload.github.com/iPERDance/iPERCore/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245258168,"owners_count":20585977,"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":"2024-07-31T15:00:54.864Z","updated_at":"2025-03-26T01:30:45.632Z","avatar_url":"https://github.com/iPERDance.png","language":"Python","readme":"# Impersonator++\n\n### Update News\n- [x] 15/04/2021, iPERCore-0.2.0, including\n  \n   * Add [Training](./docs/train_details.md)\n   \n   * Add [Novel View Synthesis](https://github.com/iPERDance/iPERCore/blob/main/docs/scripts_runner.md#run-novel-view-synthesis)\n   \n   * Add [Motion Imitation with bullet-time effects](https://github.com/iPERDance/iPERCore/blob/main/docs/scripts_runner.md#run-motion-imitation-with-bullet-time-effect)\n   \n   * Add [Motion Imitation with multi-view outputs](https://github.com/iPERDance/iPERCore/blob/main/docs/scripts_runner.md#run-motion-imitation-with-multi-view-outputs)\n   \n   * Add [Appearance Transfer](https://github.com/iPERDance/iPERCore/blob/main/docs/scripts_runner.md#run-human-appearance-transfer)\n   \n   * Add [A Unified synthesizer: Motion Imitation + Appearance Transfer + Novel View Synthesis](https://github.com/iPERDance/iPERCore/blob/main/docs/scripts_runner.md#human-appearance-transfer-with-motion-imitation-and-novel-view-synthesis)\n   \n   * Update torch 1.8+ with RTX30+ GPUs.\n  \n[comment]: \u003c\u003e (- [x] 12/20/2020, A precompiled version on Windows has been released! [[Usage]]\u0026#40;https://github.com/iPERDance/iPERCore/wiki/How-to-use-the-released-version-on-windows%3F\u0026#41;)\n- [x] 12/10/2020, iPERCore-0.1.1, supports Windows.\n- [x] 12/06/2020, iPERCore-0.1, all the base codes. The motion imitation scripts.\n\n\nSee the details of developing [logs](./docs/dev_logs.md).\n\n**Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis**, including \nhuman motion imitation, appearance transfer, and novel view synthesis. Currently the paper is under review of \nIEEE TPAMI. It is an extension of our previous ICCV project [impersonator](https://github.com/svip-lab/impersonator), \nand it has a more powerful ability in generalization and produces higher-resolution results  (512 x 512, 1024 x 1024) than the previous ICCV version.\n\n\u003c!-- |  🧾 Colab Notebook  | Released (Windows)  |   📑 Paper    | 📱 Website | 📂 Dataset | 💡 Bilibili | ✒ Forum |\n :-: | :-: | :-: | :-: | :-: | :-: | :-: |\n| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1bwUnj-9NnJA2EMr7eWO4I45UuBtKudg_?usp=sharing) | [[Usage]](https://github.com/iPERDance/iPERCore/wiki/How-to-use-the-released-version-on-windows%3F) | [paper](https://arxiv.org/pdf/2011.09055.pdf) | [website](https://www.impersonator.org/work/impersonator-plus-plus.html) | [Dataset](https://svip-lab.github.io/dataset/iPER_dataset.html) | [bilibili](https://space.bilibili.com/1018066133) | [Forum](https://iperdance.github.io/work/impersonator-plus-plus.html)| --\u003e\n\n|  🧾 Colab Notebook |   📑 Paper    | 📱 Website | 📂 Dataset | 💡 Bilibili |\n :-: | :-: | :-: | :-: | :-: |\n| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1bwUnj-9NnJA2EMr7eWO4I45UuBtKudg_?usp=sharing) | [paper](https://arxiv.org/pdf/2011.09055.pdf) | [website](https://iperdance.github.io/work/impersonator-plus-plus.html) | [Dataset](https://svip-lab.github.io/dataset/iPER_dataset.html) | [bilibili](https://space.bilibili.com/1018066133) |\n\n\n![](https://iperdance.github.io/images/motion_results.png)\n\n\n## Installation\nSee more details, including system dependencies, python requirements and setups in [install.md](./docs/install.md).\nPlease follows the instructions in [install.md](./docs/install.md) to install this firstly.\n\n**Notice that `imags_size=512` need at least 9.8GB GPU memory.** if you are using a middle-level GPU(e.g. RTX 2060), you should change the `image_size` to 384 or 256. The following table can be used as a reference:\n\n| image_size | preprocess | personalize | run_imitator | recommended gpu                    |\n| ---------- | ---------- | ----------- | ------------ | ---------------------------------- |\n| 256x256    | 3.1 GB     | 4.3 GB      | 1.1 GB       | RTX 2060 / RTX 2070                |\n| 384x384    | 3.1 GB     | 7.9 GB      | 1.5 GB       | GTX 1080Ti / RTX 2080Ti / Titan Xp |\n| 512x512    | 3.1 GB     | 9.8 GB      | 2 GB         | GTX 1080Ti / RTX 2080Ti / Titan Xp |\n| 1024x1024  | 3.1 GB     | 20 GB       | -            | RTX Titan / P40 / V100 32G         |\n\n\n## Run demos\n\n### 1. Run on Google Colab \n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1bwUnj-9NnJA2EMr7eWO4I45UuBtKudg_?usp=sharing)\n\n\n### 2. Run with Console (scripts) mode\nSee [scripts_runner](./docs/scripts_runner.md) for more details.\n\n## Citation\n```\n@article{liu2021liquid,\n  title={Liquid warping GAN with attention: A unified framework for human image synthesis},\n  author={Liu, Wen and Piao, Zhixin and Tu, Zhi and Luo, Wenhan and Ma, Lin and Gao, Shenghua},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},\n  year={2021},\n  publisher={IEEE}\n}\n\n@InProceedings{lwb2019,\n    title={Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis},\n    author={Wen Liu and Zhixin Piao, Min Jie, Wenhan Luo, Lin Ma and Shenghua Gao},\n    booktitle={The IEEE International Conference on Computer Vision (ICCV)},\n    year={2019}\n}\n```\n\n\n\n","funding_links":[],"categories":["Python","📦 Legacy \u0026 Inactive Projects","人像\\姿势\\3D人脸"],"sub_categories":["网络服务_其他"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FiPERDance%2FiPERCore","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FiPERDance%2FiPERCore","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FiPERDance%2FiPERCore/lists"}