EricGuo5513/momask-codes

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1308 stars · 116 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of MoMask (CVPR 2024), a masked modeling framework that generates 3D human motion sequences from text prompts using hierarchical vector quantization and bidirectional transformers. It includes training, evaluation, and generation scripts, plus a Hugging Face demo and a Blender add-on.

Use cases

• generate 3d human motion animations from text descriptions
• text-to-motion synthesis for characters
• temporal inpainting of motion sequences
• export bvh animations for blender or game engines
• research baseline for motion generation models
• evaluate text-driven motion generation on humanml3d

When to choose

• you need state-of-the-art text-to-motion generation with pretrained models
• you want to reproduce or extend a published CVPR 2024 motion generation method
• you need BVH output for animation pipelines like Blender

When to avoid

• you need production-ready software with long-term support
• you work outside Python/PyTorch environments
• you need real-time motion generation on low-end hardware without setup effort

Facets

library · maturity maintenance

machine-learning deep-learning animation graphics nlp machine-learning computer-vision graphics artificial-intelligence python cross-platform text-to-motion 3d-human-motion masked-modeling cvpr-2024 motion-synthesis bvh research-code transformer game-development linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="EricGuo5513/momask-codes")