InternRobotics/UniHSI
[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts
UniHSI helps simulate realistic human-object interactions in virtual environments by translating natural language commands into detailed, step-by-step movements. You provide a text description of an action (e.g., "pick up the cup") and a 3D scene, and it generates the corresponding human motion. This is for animators, robot behavior designers, or researchers developing interactive virtual agents.
245 stars. No commits in the last 6 months.
Use this if you need to generate complex, context-aware human-object interaction animations or behaviors in a simulated environment using simple text prompts.
Not ideal if you need a tool for physical robot control or real-time human motion capture for live applications.
Stars
245
Forks
14
Language
Python
License
—
Category
Last pushed
Jul 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/InternRobotics/UniHSI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zai-org/CogVideo
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
zhaorw02/DeepMesh
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
YangLing0818/RPG-DiffusionMaster
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with...
thu-nics/FrameFusion
[ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token...
Yushi-Hu/tifa
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering