HumanML3D is a 3D human motion-language dataset that originates from a combination of HumanAct12 and Amass dataset. It covers a broad range of human actions such as daily activities (e.g., 'walking', 'jumping'), sports (e.g., 'swimming', 'playing golf'), acrobatics (e.g., 'cartwheel') and artistry (e.g., 'dancing'). Overall, HumanML3D dataset consists of 14,616 motions and 44,970 descriptions composed by 5,371 distinct words. The total length of motions amounts to 28.59 hours. The average motion length is 7.1 seconds, while average description length is 12 words.
arxiv-sanity
Awesome-Motion-Diffusion-Models 系列论文列表 - 知乎
PDF] Generating Diverse and Natural 3D Human Motions from Text
3D Body Keypoint Datasets — MMPose 1.3.1 documentation
Generating Diverse and Natural 3D Human Motions from Texts
VQ-VAE motion reconstruction results on HumanML3D[16] test set. ↑ / ↓
Human3.6M Dataset
2307.00818] Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Creating Authentic Human Motion Synthesis via Diffusion - Metaphysic.ai
Generate Movement from Text Descriptions with T2M-GPT - Voxel51
Experiments of MotionGPT (Spring 2023) - Human Motion Synthesis
2307.00818] Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Cross-Modal Retrieval for Motion and Text via DropTriple Loss
Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
2307.00818] Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset