Silverster98/HUMANISE
Official implementation of the NeurIPS22 paper "HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes"
This project helps 3D animators and game developers create realistic human movements within virtual environments. By providing a 3D scene and a simple text description (like "sit on the armchair near the desk"), it generates natural human motion that interacts appropriately with the scene. The primary users are professionals in animation, virtual reality, and game design who need to populate 3D spaces with believable character actions.
145 stars. No commits in the last 6 months.
Use this if you need to quickly generate diverse, semantically consistent 3D human motions interacting with specific objects in a virtual scene based on natural language commands.
Not ideal if you need fine-grained, manual control over every joint and keyframe of an animation or are working with highly specialized, non-standard character rigs.
Stars
145
Forks
7
Language
Python
License
MIT
Category
Last pushed
Nov 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Silverster98/HUMANISE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tamasino52/U-CondDGCN
Unofficial pytorch implementation of U-CondDGCN from "WenBo Hu, Changgong Zhang, Fangneng Zhan,...
UPC-ViRVIG/SparsePoser
Official Code for ACM Transactions on Graphics (TOG) paper "SparsePoser: Real-time Full-body...
syguan96/DynaBOA
[T-PAMI 2022] Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation