English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Haar Wavelet based Block Autoregressive Flows for Trajectories

MPS-Authors
/persons/resource/persons197297

Bhattacharyya,  Apratim
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

External Ressource
No external resources are shared
Fulltext (public)

arXiv:2009.09878.pdf
(Preprint), 6MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Bhattacharyya, A., Straehle, C.-N., Fritz, M., & Schiele, B. (2020). Haar Wavelet based Block Autoregressive Flows for Trajectories. Retrieved from https://arxiv.org/abs/2009.09878.


Cite as: http://hdl.handle.net/21.11116/0000-0007-80EF-B
Abstract
Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GANs and VAEs for learning the likely future trajectories, accurately modeling the dependency structure of these multimodal distributions, particularly over long time horizons remains challenging. Normalizing flow based generative models can model complex distributions admitting exact inference. These include variants with split coupling invertible transformations that are easier to parallelize compared to their autoregressive counterparts. To this end, we introduce a novel Haar wavelet based block autoregressive model leveraging split couplings, conditioned on coarse trajectories obtained from Haar wavelet based transformations at different levels of granularity. This yields an exact inference method that models trajectories at different spatio-temporal resolutions in a hierarchical manner. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets - Stanford Drone and Intersection Drone.