# Haar Wavelet based Block Autoregressive Flows for Trajectories

arXiv: https://arxiv.org/abs/2009.09878 · HTML: https://mlsanity.com/paper/2009.09878/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [FloMo: Tractable Motion Prediction with Normalizing Flows](https://mlsanity.com/paper/2103.03614/) (2021)
- [Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers](https://mlsanity.com/paper/2106.12442/) (2021)
- [Under the Hood of Transformer Networks for Trajectory Forecasting](https://mlsanity.com/paper/2203.11878/) (2022)
- [Vision-based Multi-future Trajectory Prediction: A Survey](https://mlsanity.com/paper/2302.10463/) (2023)
- [ASTRA: A Scene-aware TRAnsformer-based model for trajectory prediction](https://mlsanity.com/paper/2501.09878/) (2025)
- [PixelPyramids: Exact Inference Models from Lossless Image Pyramids](https://mlsanity.com/paper/2110.08787/) (2021)

## Abstract (arXiv)

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.