tr3e/InterGen
[IJCV 2024] InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions
Employs a diffusion-based architecture with explicit world-frame motion representation to capture spatial relations between two performers, incorporating novel regularization terms to enforce interaction constraints. Supports diverse downstream tasks including person-to-person generation, motion inbetweening, and trajectory control through text conditioning. Includes the InterHuman dataset (107M frames of paired skeletal motion with natural language descriptions) and inference pipeline compatible with SMPL skeletal format.
312 stars. No commits in the last 6 months.
Stars
312
Forks
26
Language
Python
License
—
Category
Last pushed
Jul 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tr3e/InterGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InhwanBae/Crowd-Behavior-Generation
Official Code for "Continuous Locomotive Crowd Behavior Generation (CVPR 2025)"
InhwanBae/SingularTrajectory
Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"
XinGP/DGFNet
[RAL 2025]Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network
DSL-Lab/MoFlow
[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum...
InhwanBae/GraphTERN
Official Code for "A Set of Control Points Conditioned Pedestrian Trajectory Prediction (AAAI 2023)"