{"id":18427684,"url":"https://github.com/eldar/deepcut","last_synced_at":"2025-04-13T19:46:03.247Z","repository":{"id":66937302,"uuid":"61859514","full_name":"eldar/deepcut","owner":"eldar","description":"Multi Person Pose Estimation","archived":false,"fork":false,"pushed_at":"2016-08-30T15:02:12.000Z","size":282,"stargazers_count":222,"open_issues_count":10,"forks_count":83,"subscribers_count":20,"default_branch":"master","last_synced_at":"2025-02-16T08:27:54.706Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Matlab","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/eldar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2016-06-24T05:39:52.000Z","updated_at":"2025-02-15T21:58:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"fd0ab137-1fe8-449c-a4f8-61f661b1b66a","html_url":"https://github.com/eldar/deepcut","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/eldar%2Fdeepcut","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eldar%2Fdeepcut/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eldar%2Fdeepcut/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eldar%2Fdeepcut/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eldar","download_url":"https://codeload.github.com/eldar/deepcut/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248772778,"owners_count":21159344,"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":"2024-11-06T05:11:30.890Z","updated_at":"2025-04-13T19:46:03.227Z","avatar_url":"https://github.com/eldar.png","language":"Matlab","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep(er)Cut: Multi Person Pose Estimation\n\nThis short documentation describes steps necessary to compile and run the code that implements [DeepCut](http://arxiv.org/abs/1511.06645) and [DeeperCut](http://arxiv.org/abs/1605.03170) papers:\t\n\n**Leonid Pishchulin, Eldar Insafutdinov, Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, Peter Gehler, and Bernt Schiele\t\t\t  \nDeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation\t       \nIn _IEEE Conference on Computer Vision and Pattern Recognition (CVPR)_, 2016**\t       \n\n**Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele   \nDeeperCut:  A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model   \nIn _European Conference on Computer Vision (ECCV)_, 2016**\t\nFor more information visit http://pose.mpi-inf.mpg.de\n\n## Prerequisites\n- This code was developed under Linux (Debian wheezy, 64 bit) and was tested only in this environment.\n- HDF5 1.8\n- CMake\n- C++ 11\n- CUDA \u003e=7.5\n- [Caffe building instructions](http://caffe.berkeleyvision.org/installation.html)\n- [Gurobi optimizer 6.0.x](https://user.gurobi.com/download/gurobi-optimizer)\n\n## Installation Instructions\n\n1. Clone repository\t\n   ```\n   $ git clone https://github.com/eldar/deepcut --recursive\n   ```\n\n2. Build Caffe and its MATLAB interface after configuring `Makefile.config`\t\n   ```\n   $ cd external/caffe\n   $ make -j 4 all matcaffe\n   ```\n\n3. Build `liblinear`, specify the path to the MATLAB installation\t\n   ```\n   $ cd external/liblinear-1.94/matlab\n   $ CC=gcc CXX=g++ MATLABDIR=/usr/lib/matlab-8.6/ make\n   ```\n\n4. Build solver\t\n   ```\n   $ cd external/solver\n   $ cmake . -DGUROBI_ROOT_DIR=/path/to/gurobi603/linux64 -DGUROBI_VERSION=60\n   $ make solver-callback\n   ```\n\n5. Obtain Gurobi license from http://www.gurobi.com/downloads/licenses/license-center\n   and place the license file license.lic in data/gurobi or modify parameter \n   p.gurobi_license_file in lib/pose/exp_params.m to point to the license file location\n\n## Download models\n```\n$ cd data\n$ ./download_models.sh\n```\n\n## Run Demo\t\n```\n$ cd \u003croot_dir\u003e\n$ ./start_matlab.sh\n% in MATLAB\n\u003e\u003e demo_multiperson\n```\n\n## CNN-based part detectors\n\nAccess [DeeperCut Part Detectors](https://github.com/eldar/deepcut-cnn) to download stand-alone part detectors that produce dense scoremaps.\n\n## Citing\n```\n@inproceedings{insafutdinov2016deepercut,\n\tauthor = {Eldar Insafutdinov and Leonid Pishchulin and Bjoern Andres and Mykhaylo Andriluka and Bernt Schieke},\n\ttitle = {DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model},\n\tbooktitle = {European Conference on Computer Vision (ECCV)},\n\tyear = {2016},\n\turl = {http://arxiv.org/abs/1605.03170}\n    }\n@inproceedings{pishchulin16cvpr,\n\tauthor = {Leonid Pishchulin and Eldar Insafutdinov and Siyu Tang and Bjoern Andres and Mykhaylo Andriluka and Peter Gehler and Bernt Schiele},\n\ttitle = {DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation},\n\tbooktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n\tyear = {2016},\n\turl = {http://arxiv.org/abs/1511.06645}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feldar%2Fdeepcut","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feldar%2Fdeepcut","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feldar%2Fdeepcut/lists"}