The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributions. 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. This provides the first benchmark for quantitative evaluation of the models to predict multi-future trajectories. The second contribution is a new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs. We refer to our model as Multiverse. We show that our model achieves the best results on our dataset, as well as on the real-world VIRAT/ActEV dataset (which just contains one possible future).

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Trajectory Prediction ActEV Multiverse ADE-8/12 18.51 # 4
FDE-8/12 35.84 # 3
Multi-future Trajectory Prediction ForkingPaths Multiverse ADE 168.9 # 1
FDE 333.8 # 1
Trajectory Forecasting ForkingPaths Multiverse ADE 168.9 # 1
Trajectory Prediction ForkingPaths Multiverse ADE 168.9 # 1
Trajectory Prediction Stanford Drone Multiverse ADE-8/12 @K = 20 14.78 # 12
FDE-8/12 @K= 20 27.09 # 12


No methods listed for this paper. Add relevant methods here