-
[pdf]
[supp]
[bibtex]@InProceedings{Dendorfer_2021_ICCV, author = {Dendorfer, Patrick and Elflein, Sven and Leal-Taix\'e, Laura}, title = {MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {13158-13167} }
MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction
Abstract
Pedestrian trajectory prediction is challenging due to its uncertain and multimodal nature. While generative adversarial networks can learn a distribution over future trajectories, they tend to predict out-of-distribution samples when the distribution of future trajectories is a mixture of multiple, possibly disconnected modes. To address this issue, we propose a multi-generator model for pedestrian trajectory prediction. Each generator specializes in learning a distribution over trajectories routing towards one of the primary modes in the scene, while a second network learns a categorical distribution over these generators, conditioned on the dynamics and scene input. This architecture allows us to effectively sample from specialized generators and to significantly reduce the out-of-distribution samples compared to single generator methods.
Related Material