{"id":13680236,"url":"https://github.com/XinArkh/VNect","last_synced_at":"2025-04-29T23:30:55.498Z","repository":{"id":43673138,"uuid":"163192215","full_name":"XinArkh/VNect","owner":"XinArkh","description":"Real-time 3D human pose estimation, implemented by tensorflow","archived":false,"fork":false,"pushed_at":"2024-07-24T03:37:33.000Z","size":28797,"stargazers_count":248,"open_issues_count":1,"forks_count":40,"subscribers_count":12,"default_branch":"master","last_synced_at":"2024-11-11T23:37:19.347Z","etag":null,"topics":["3d-human-pose","human-pose-estimation","vnect"],"latest_commit_sha":null,"homepage":"","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/XinArkh.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-12-26T15:14:16.000Z","updated_at":"2024-11-04T14:53:02.000Z","dependencies_parsed_at":"2024-08-02T13:29:35.495Z","dependency_job_id":null,"html_url":"https://github.com/XinArkh/VNect","commit_stats":{"total_commits":103,"total_committers":2,"mean_commits":51.5,"dds":0.009708737864077666,"last_synced_commit":"6516c5a5e1fd5f9a5cfaad9679d480c63e4ec7ad"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XinArkh%2FVNect","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XinArkh%2FVNect/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XinArkh%2FVNect/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XinArkh%2FVNect/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/XinArkh","download_url":"https://codeload.github.com/XinArkh/VNect/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251599806,"owners_count":21615586,"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":["3d-human-pose","human-pose-estimation","vnect"],"created_at":"2024-08-02T13:01:14.589Z","updated_at":"2025-04-29T23:30:50.995Z","avatar_url":"https://github.com/XinArkh.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# VNect\n\nA tensorflow implementation of [VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera](http://gvv.mpi-inf.mpg.de/projects/VNect/).\n\nFor the caffe model/weights required in the repository: please contact [the author of the paper](http://gvv.mpi-inf.mpg.de/projects/VNect/).\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./pic/test_pic_show.png\" height=\"260\"\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./pic/test_video_show.gif\" height=\"300\"\u003e\n\u003c/p\u003e\n\n\n## Environments\n\n- Python 3.x\n- tensorflow-gpu 1.x\n- [pycaffe](https://github.com/BVLC/caffe/tree/windows)\n\n\n## Usage\n\n### Preparation\n\n1. Drop the pretrained caffe model into `models/caffe_model`.\n2. Run `init_weights.py` to generate tensorflow model weights.\n\n### Scripts\n\n1. `run_estimator.py` is a script for **video stream**.\n2. **(Recommended)** `run_estimator_ps.py` is a **multiprocessing** version script. Notice that in `run_estimator.py`, the 3D plotting function may shut down occasionally depending on the matplotlib version . `run_estimator_ps.py` resolves this issue.\n3. `run_pic.py` is a script for a **picture**.\n\n\u003cdetails\u003e\u003csummary\u003e \u003c/summary\u003e\n\n4. **(Deprecated)** `benchmark.py` is a class implementation containing all the elements needed to run the model.\n5. **(Deprecated)** `run_estimator_robot.py` additionally provides ROS network and/or serial connection for communication in robot controlling.\n6. **(Deprecated)** The training script `train.py` is not complete yet (I failed to reconstruct the model: ( So do not use it. Also pulling requests are welcomed.\n\n\u003c/details\u003e\n\n\n**[Tips]** To run the scripts for video stream:\n\n1.  click left mouse button to initialize the bounding box implemented by a simple HOG method;\n\n2. trigger any keyboard input to exit while running.\n\n## Notes\n\n1. With some certain programming environments, the 3D plotting function (by matplotlib) in `run_estimator.py` shuts down. In this case, use `run_estimator_ps.py` instead.\n2. The input image is in BGR color format and the pixel value is mapped into a range of [-0.4, 0.6).\n3. The joint-parent map (detailed information in `materials/joint_index.xlsx`):\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./pic/joint_index.png\" height=\"300\"\u003e\n\u003c/p\u003e\n\n4. Here I have a sketch to show the joint positions (don't laugh lol):\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./pic/joint_pos.jpg\" height=\"300\"\u003e\n\u003c/p\u003e\n\n5. Every input image is assumed to contain 21 joints to be found, which means it is easy to fit wrong results when a joint is actually not in the picture.\n\n## About Training Data\n\nFor MPI-INF-3DHP dataset, refer to [my another repository](https://github.com/XinArkh/mpi_inf_3dhp).\n\n## Reference Repositories\n\n- original MATLAB implementation provided by the paper author.\n- [timctho/VNect-tensorflow](https://github.com/timctho/VNect-tensorflow)\n- [EJShim/vnect_estimator](https://github.com/EJShim/vnect_estimator)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXinArkh%2FVNect","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FXinArkh%2FVNect","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXinArkh%2FVNect/lists"}