InhwanBae/Crowd-Behavior-Generation
Official Code for "Continuous Locomotive Crowd Behavior Generation (CVPR 2025)"
This project helps create realistic, continuous crowd movements for virtual environments or simulations. By inputting a single scene image, it outputs detailed, lifelong trajectories for individual people, including dynamic entries and exits from the scene. It's ideal for animators, urban planners, or researchers who need to simulate complex crowd behaviors.
Use this if you need to generate believable, ever-changing crowd movements within a given scene layout, without needing pre-recorded individual paths.
Not ideal if you need to control specific individual agent actions or interactions in a rule-based manner, rather than generating emergent behaviors.
Stars
44
Forks
8
Language
Python
License
MIT
Category
Last pushed
Nov 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/InhwanBae/Crowd-Behavior-Generation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
InhwanBae/SingularTrajectory
Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"
DSL-Lab/MoFlow
[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum...
XinGP/DGFNet
[RAL 2025]Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network
qiyan98/social-nce-stgcnn
[ICCV'21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware...
InhwanBae/GraphTERN
Official Code for "A Set of Control Points Conditioned Pedestrian Trajectory Prediction (AAAI 2023)"