{"url":"/dataset/humanrig","name":"HumanRig","full_name":null,"description_markdown":"### Overview\r\n\r\n- **Dataset Name**: HumanRig\r\n- **Paper**: CVPR2025 - \"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset\"\r\n- **Authors**: [Zedong Chu · Feng Xiong · Meiduo Liu · Jinzhi Zhang · Mingqi Shao · Zhaoxu Sun · Di Wang · Mu Xu]\r\n- \r\nThe HumanRig dataset is introduced in the CVPR2025 paper titled \"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset\". This work addresses the critical need for a comprehensive dataset and a robust framework for automatic rigging of 3D humanoid character models. HumanRig is a large-scale dataset of AI-generated T-pose humanoid models, all rigged with a consistent skeleton topology. It significantly surpasses previous datasets in terms of size, diversity, complexity, and practical motion applications.\r\n\r\n### Dataset Details\r\n\r\n- **Number of Samples**: 11,434\r\n- **Data Splits**:\r\n  - **Training Set**: 0-9147 (80%)\r\n  - **Validation Set**: 9148-10290 (10%)\r\n  - **Test Set**: 10291-11433 (10%)\r\n\r\n### Data Structure\r\n\r\nEach annotated sample in the HumanRig dataset includes the following components:\r\n\r\n- **Rigged T-pose Humanoid Mesh**: A rigged 3D mesh of the humanoid character in T-pose.\r\n- **3D Skeleton Joint Positions**: The positions of the joints in the 3D skeleton.\r\n- **Skinning Weight Matrix**: A matrix that defines the influence of each joint on the vertices of the mesh.\r\n- **Front-view Image**: A 2D image of the humanoid character from the front view.\r\n- **Camera Parameters**: The parameters of the camera used to capture the front-view image.\r\n- **2D Skeleton Joint Positions**: The positions of the joints in the 2D front-view image.\r\n\r\n### Skeleton Joint Order\r\n\r\nThe skeleton joints in the dataset follow a specific order:\r\n\r\n```python\r\n['Hips', 'Spine', 'Spine1', 'Spine2', 'Neck', 'Head', 'LeftShoulder', 'LeftArm', 'LeftForeArm', 'LeftHand', 'RightShoulder', 'RightArm', 'RightForeArm', 'RightHand', 'LeftUpLeg', 'LeftLeg', 'LeftFoot', 'LeftToeBase', 'RightUpLeg', 'RightLeg', 'RightFoot', 'RightToeBase']\r\n```\r\n\r\n### Citation\r\n\r\nIf you use the HumanRig dataset in your research, please cite the following paper:\r\n\r\n```bibtex\r\n@article{chu2024humanrig,\r\n  title={HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset},\r\n  author={Chu, Zedong and Xiong, Feng and Liu, Meiduo and Zhang, Jinzhi and Shao, Mingqi and Sun, Zhaoxu and Wang, Di and Xu, Mu},\r\n  journal={arXiv preprint arXiv:2412.02317},\r\n  year={2024}\r\n}\r\n```","description_withheld":null,"homepage":"https://c8241998.github.io/HumanRig/","introduced_date":"2024-12-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/humanrig-learning-automatic-rigging-for","title":"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset","first_author":"Zedong Chu","url":null},"license":{"name":"cc-by-nc-4.0","url":null},"modalities":[],"tasks":[{"name":"3D Generation","url":"/task/3d-generation","datasets_with_task":"/datasets/task/3d-generation"}],"languages":[],"variants":["HumanRig"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}