InhwanBae/SingularTrajectory

Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"

39
/ 100
Emerging

This project helps you predict human movement patterns across various scenarios, such as pedestrian flow in public spaces. It takes historical trajectory data as input and generates likely future paths, even with limited observations. The system is designed for researchers or practitioners working with crowd analysis, robotics, or surveillance applications.

145 stars. No commits in the last 6 months.

Use this if you need a robust, general-purpose model for predicting diverse human movements in crowded environments or for tasks with varying data availability.

Not ideal if you require real-time, ultra-low-latency predictions for safety-critical autonomous systems, as the focus is on accuracy over speed for research benchmarks.

crowd-behavior-prediction human-trajectory-forecasting robot-navigation surveillance-analytics pedestrian-dynamics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

145

Forks

11

Language

Python

License

Last pushed

Jul 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/InhwanBae/SingularTrajectory"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.