Search Results for author: Julien Pettre

Found 4 papers, 3 papers with code

What we see and What we don't see: Imputing Occluded Crowd Structures from Robot Sensing

no code implementations17 Sep 2021 Javad Amirian, Jean-Bernard Hayet, Julien Pettre

We address the problem of inferring the human occupancy in the space around the robot, in blind spots, beyond the range of its sensing capabilities.

Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs

1 code implementation CVPR 2019 Javad Amirian, Jean-Bernard Hayet, Julien Pettre

We show through experiments on real and synthetic data that the proposed method leads to generate more diverse samples and to preserve the modes of the predictive distribution.

 Ranked #1 on Trajectory Prediction on Stanford Drone (FDE (in world coordinates) metric)

Generative Adversarial Network Human motion prediction +4

Cannot find the paper you are looking for? You can Submit a new open access paper.