{"id":14036932,"url":"https://github.com/isarandi/synthetic-occlusion","last_synced_at":"2025-04-14T09:34:50.450Z","repository":{"id":79994328,"uuid":"148613948","full_name":"isarandi/synthetic-occlusion","owner":"isarandi","description":"Synthetic Occlusion Augmentation","archived":false,"fork":false,"pushed_at":"2020-03-08T19:06:28.000Z","size":382,"stargazers_count":114,"open_issues_count":0,"forks_count":19,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-08-13T03:06:12.132Z","etag":null,"topics":["computer-vision","data-augmentation","occlusion","python","synthetic-dataset-generation"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/isarandi.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":"2018-09-13T09:21:52.000Z","updated_at":"2024-05-10T13:37:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"3b67f2f4-0329-4664-8cf0-17b3dfd15f5f","html_url":"https://github.com/isarandi/synthetic-occlusion","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/isarandi%2Fsynthetic-occlusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isarandi%2Fsynthetic-occlusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isarandi%2Fsynthetic-occlusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isarandi%2Fsynthetic-occlusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/isarandi","download_url":"https://codeload.github.com/isarandi/synthetic-occlusion/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224866880,"owners_count":17382876,"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":["computer-vision","data-augmentation","occlusion","python","synthetic-dataset-generation"],"created_at":"2024-08-12T03:02:20.269Z","updated_at":"2024-11-16T01:40:10.223Z","avatar_url":"https://github.com/isarandi.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Synthetic Occlusion Data Augmentation\n\n![Occlusion augmented examples](examples.jpg)\n\nIn computer vision, synthetically augmenting training input images by pasting objects onto them has been shown to improve performance across several tasks, including object detection, facial landmark localization and human pose estimation.\n\nSuch pasting is also useful for evaluating a model's robustness to (synthetic) occlusions appearing on the test inputs.\n\nThis is the implementation we used in our [IROS'18 workshop paper](https://arxiv.org/abs/1808.09316) to study occlusion-robustness in 3D human pose estimation, and to achieve first place in the 2018 ECCV PoseTrack Challenge on 3D human pose estimation. Method description and detailed results for the latter can be found in [our short paper on arXiv](https://arxiv.org/abs/1809.04987).\n\nContact: István Sárándi \u003csarandi@vision.rwth-aachen.de\u003e\n\n## Dependencies \nYou'll need the scientific Python stack (with Python 3), OpenCV and Pillow to run this code.\n\n## Getting Started\n\nClone the repo.\n\n```bash\ngit clone https://github.com/isarandi/synthetic-occlusion.git\ncd synthetic-occlusion\n```\n\nDownload and extract the Pascal VOC training/validation data (2 GB).\n\n```bash\nwget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar\ntar -xf VOCtrainval_11-May-2012.tar\n\n```\n\nTest if it works (after some time this should show occluded examples of the \"astronaut\" image, like above).\n\n```bash\n./augmentation.py VOCdevkit/VOC2012\n```\n\n## Example Use in Python\n\n```python \noccluders = load_occluders(pascal_voc_path=PATH_TO_THE_VOC2012_DIR)\nexample_image = cv2.resize(skimage.data.astronaut(), (256,256))\noccluded_image = occlude_with_objects(example_image, occluders)\n```\n\n\n## References\n\n[1] I. Sárándi; T. Linder; K. O. Arras; B. Leibe: \"[How Robust is 3D Human Pose Estimation to Occlusion?](https://arxiv.org/abs/1808.09316)\" in IEEE/RSJ Int. Conference on Intelligent Robots and Systems (IROS'18) Workshops (2018) arXiv:1808.09316\n\n[2] I. Sárándi; T. Linder; K. O. Arras; B. Leibe: \"[Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation](https://arxiv.org/abs/1809.04987)\" (extended abstract) ECCV Workshops (2018) arXiv:1809.04987\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisarandi%2Fsynthetic-occlusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fisarandi%2Fsynthetic-occlusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisarandi%2Fsynthetic-occlusion/lists"}