trajectory-forecasting

Code for "Transformer Networks for Trajectory Forecasting"

[ICCV 2021] Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs (CVPR 2019)

Code for: "Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation" Accepted @ ECCV2022

PyTorch code for ICPR 2020 paper "DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting"

The official implementation of "Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting" presented in ECCV2022.

Code for: "Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs", ICCV2021 Workshops

This repository is a paper digest of multi-agent behavior (motion / trajectory) prediction (forecasting / generation).

Collection of Papers in Trajectory Prediction categorised according to the high-level structure

Forecast where tracked objects will move next. A lightweight extension to Ultralytics YOLO that adds Kalman-filtered trajectory prediction; stable, low-jitter, and efficient for real-time systems.

Official source code for "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems". In NeurIPS 2021.

Official source code for "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields". In NeurIPS 2023.

USV simulator for dynamic and curvature-based trajectory forecasting

Kinematic Expert Factorization for Multimodal Trajectory Forecasting — AV trajectory prediction with CVAE, physics experts, and CFCP regularization.

Probabilistic pedestrian forecasts from a handheld phone: world-frame heat maps, visual-inertial height drift and evaluation without ground truth. Code, pre-registered protocol and paper sources.