CISPA
Browse

Haar Wavelet based Block Autoregressive Flows for Trajectories

Download (5.73 MB)
conference contribution
posted on 2023-11-29, 18:15 authored by Apratim Bhattacharyya, Christoph-Nikolas Straehle, Mario FritzMario Fritz, Bernt Schiele
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.

History

Preferred Citation

Apratim Bhattacharyya, Christoph-Nikolas Straehle, Mario Fritz and Bernt Schiele. Haar Wavelet based Block Autoregressive Flows for Trajectories. In: German Conference on Pattern Recognition (GCPR). 2020.

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

German Conference on Pattern Recognition (GCPR)

Legacy Posted Date

2021-02-18

Open Access Type

  • Green

BibTeX

@inproceedings{cispa_all_3365, title = "Haar Wavelet based Block Autoregressive Flows for Trajectories", author = "Bhattacharyya, Apratim and Straehle, Christoph-Nikolas and Fritz, Mario and Schiele, Bernt", booktitle="{German Conference on Pattern Recognition (GCPR)}", year="2020", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC