Trajectory Forecasting
28 papers with code • 3 benchmarks • 6 datasets
Trajectory forecasting is a sequential prediction task, where a forecasting model predicts future trajectories of all moving agents (humans, vehicles, etc.) in a scene, based on their past trajectories and/or the scene context.
(Illustrative figure from Social NCE: Contrastive Learning of Socially-aware Motion Representations)
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
UCY
JAAD
TrajNet
PIE
NBA SportVU
Greatest papers with code
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
agrimgupta92/sgan
•
•
CVPR 2018
Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments.
Ranked #12 on
Trajectory Prediction
on ETH/UCY
Argoverse: 3D Tracking and Forecasting with Rich Maps
In our baseline experiments, we illustrate how detailed map information such as lane direction, driveable area, and ground height improves the accuracy of 3D object tracking and motion forecasting.
Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
StanfordASL/Trajectron-plus-plus
•
•
ECCV 2020
Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation.
Ranked #7 on
Trajectory Prediction
on nuScenes
OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets
Human Trajectory Prediction (HTP) has gained much momentum in the last years and many solutions have been proposed to solve it.
Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models
vincent-leguen/STDL
•
•
NeurIPS 2019
We introduce a differentiable loss function suitable for training deep neural nets, and provide a custom back-prop implementation for speeding up optimization.
SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras
We refer to our method as SimAug.
Ranked #1 on
Trajectory Prediction
on ActEV
The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
JunweiLiang/Multiverse
•
•
CVPR 2020
The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals.
Ranked #1 on
Trajectory Forecasting
on ForkingPaths
Transformer Networks for Trajectory Forecasting
FGiuliari/Trajectory-Transformer
•
•
In particular, the TF model without bells and whistles yields the best score on the largest and most challenging trajectory forecasting benchmark of TrajNet.
Ranked #5 on
Trajectory Prediction
on ETH/UCY
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
HarshayuGirase/PECNet
•
•
ECCV 2020
In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction.
Ranked #1 on
Multi-future Trajectory Prediction
on ETH/UCY
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs
amiryanj/socialways
•
•
CVPR 2019
We show through experiments on real and synthetic data that the proposed method leads to generate more diverse samples and to preserve the modes of the predictive distribution.
Human motion prediction
Multi-future Trajectory Prediction
+3