{"id":22382270,"url":"https://github.com/googleinterns/humangps","last_synced_at":"2025-10-28T15:09:16.548Z","repository":{"id":49435938,"uuid":"366734243","full_name":"googleinterns/humangps","owner":"googleinterns","description":null,"archived":false,"fork":false,"pushed_at":"2021-06-26T04:29:25.000Z","size":34981,"stargazers_count":60,"open_issues_count":3,"forks_count":10,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-06T18:50:40.627Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/googleinterns.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-05-12T13:57:28.000Z","updated_at":"2025-03-26T08:11:25.000Z","dependencies_parsed_at":"2022-08-04T08:30:11.871Z","dependency_job_id":null,"html_url":"https://github.com/googleinterns/humangps","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/googleinterns/humangps","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/googleinterns%2Fhumangps","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/googleinterns%2Fhumangps/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/googleinterns%2Fhumangps/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/googleinterns%2Fhumangps/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/googleinterns","download_url":"https://codeload.github.com/googleinterns/humangps/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/googleinterns%2Fhumangps/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267983365,"owners_count":24176058,"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","status":"online","status_checked_at":"2025-07-31T02:00:08.723Z","response_time":66,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2024-12-05T00:12:21.464Z","updated_at":"2025-10-28T15:09:16.451Z","avatar_url":"https://github.com/googleinterns.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences\n\nTensorflow implementation of the paper \"HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences\", CVPR 2021.\n\n### [Project Page](https://feitongt.github.io/HumanGPS/) | [Videos](https://feitongt.github.io/HumanGPS/#Vis_feature) | [Paper](https://arxiv.org/pdf/2103.15573.pdf) | [Data]()\n\n## Setup\n\n* Python 3.6\n* TensorFlow 2.0\n* Tensorflow-Addon\n* gin-config\n* scikit-learn\n\n```sh\npip install -r requirements.txt  --user\npip install gdown\n```\n\n## Running code\n\nHere we show how to run our code on SMPL intra and inter testing data. You can download the rest of the synthetic SMPL testing data used in the paper [here]().\n\n### 1. Download pretrained model.\n\n```sh\nbash download_model.sh\n```\n\n### 2. Evaluate on intra testing data.\n\n(a) Run\n\n```sh\nmkdir -p ./test_data/\n```\n\nDownload our SMPL intra test data from [smpl_intra_data](https://www.icloud.com/iclouddrive/0UmpxsQ3btifW8F67ENT6chng#smpl%5Fintra%5Ftest) in `./test_data/`\n\nTo evaluate average epe on intra test dataset.\n\n(b) set `JOB_NAME=\"eval_optical_flow_intra\"` in `./script/inference_local.sh`\n\n(c) Run\n\n```sh\nbash ./script/inference_local.sh\n```\n\n### 3. Evaluate on inter testing data. \n\n(a) Run\n\n```sh\nmkdir -p ./test_data/\n```\nDownload our SMPL inter test data from [smpl_inter_data](https://www.icloud.com/iclouddrive/0fC-vqM9UCK-kl2KA56f4OwqA#smpl%5Finter%5Ftest) in `./test_data/`\n\nTo evaluate average epe on inter test dataset.\n\n(b) set `JOB_NAME=\"eval_optical_flow_inter\"` in `./script/inference_local.sh`\n\n(c) Run\n\n```sh\nbash ./script/inference_local.sh\n```\n\n### 4. Train on intra testing data.\nCurrently, we can not provide the whole training dataset due to the copyright and huge size of the data.\n\nHere, we provide an example configuration for training on intra testing data.\n```sh\nbash ./script/train_local.sh\n```\n\n### 5. Inference on toy examples for visualization.\n\nCheck out `./inference_demo.ipynb` for toy examples.\n\n## Citation\n\nIf you find this code useful in your research, please cite:\n\n```bibtex\n@inproceedings{tan2021humangps,\n  title = {{HumanGPS: Geodesic PreServing Feature for Dense Human Correspondence}},\n  author = {Tan, Feitong and Tang, Danhang and Dou, Mingsong and Guo, Kaiwen and Pandey, Rohit and Keskin, Cem and Du, Ruofei and Sun, Deqing and Bouaziz, Sofien and Fanello, Sean and Tan, Ping and Zhang, Yinda},\n  booktitle = {2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year = {2021},\n  publisher = {IEEE},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogleinterns%2Fhumangps","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoogleinterns%2Fhumangps","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogleinterns%2Fhumangps/lists"}