DSL-Lab/MoFlow
[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation Distillation
This project helps predict the future movements of people or objects in a scene, like basketball players on a court or pedestrians in a park. You provide past trajectory data, and it generates multiple plausible future paths for all agents, showing both the most likely route and alternative possibilities. It's designed for researchers or analysts working with human behavior modeling and spatial prediction.
107 stars.
Use this if you need to accurately forecast diverse future trajectories for multiple interacting agents, such as in sports analytics, urban planning, or autonomous systems research.
Not ideal if you only need a single, deterministic prediction and don't require understanding the uncertainty or generating a range of possible future movements.
Stars
107
Forks
5
Language
Python
License
MIT
Category
Last pushed
Dec 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DSL-Lab/MoFlow"
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
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)"