Vehicle trajectory prediction works, but not everywhere

M Bahari, S Saadatnejad, A Rahimi… - Proceedings of the …, 2022 - openaccess.thecvf.com
Vehicle trajectory prediction is nowadays a fundamental pillar of self-driving cars. Both the
industry and research communities have acknowledged the need for such a pillar by …

A generic diffusion-based approach for 3d human pose prediction in the wild

S Saadatnejad, A Rasekh, M Mofayezi… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Predicting 3D human poses in real-world scenarios, also known as human pose forecasting,
is inevitably subject to noisy inputs arising from inaccurate 3D pose estimations and …

Stay on track: A frenet wrapper to overcome off-road trajectories in vehicle motion prediction

M Hallgarten, I Kisa, M Stoll… - 2024 IEEE Intelligent …, 2024 - ieeexplore.ieee.org
Predicting the future motion of surrounding vehicles is a crucial enabler for safe autonomous
driving. The field of motion prediction has seen large progress recently with State-of-the-Art …

Social-transmotion: Promptable human trajectory prediction

S Saadatnejad, Y Gao, K Messaoud, A Alahi - arxiv preprint arxiv …, 2023 - arxiv.org
Accurate human trajectory prediction is crucial for applications such as autonomous
vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage …

Joint feature modulation mechanism for driving scene image synthesis by instance texture edge and spatial depth priors

Y **e, H Qin, G Chen, J Yang, B Feng - International Journal of Machine …, 2024 - Springer
In this paper, we study Conditional Image Synthesis (CIS) task towards producing
photorealistic driving scenes, which plays a significant role in designing perception …

Boosting Visual Fidelity in Driving Simulations through Diffusion Models

F Bu, H Yasuda - arxiv preprint arxiv:2410.04214, 2024 - arxiv.org
Diffusion models have made substantial progress in facilitating image generation and
editing. As the technology matures, we see its potential in the context of driving simulations …

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

S Saadatnejad - 2023 - infoscience.epfl.ch
Forecasting is a capability inherent in humans when navigating. Humans routinely plan their
paths, considering the potential future movements of those around them. Similarly, to …

Varied Realistic Autonomous Vehicle Collision Scenario Generation

M Priisalu, C Paduraru, C Smichisescu - Scandinavian Conference on …, 2023 - Springer
Recently there has been an increase in the number of available autonomous vehicle (AV)
models. To evaluate and compare the safety of the various models the AVs need to be …

Unsupervised Domain Adaptation using Satellite Images for Significantly Different Infrastructure Objects

M Sokolov - 2022 - winnspace.uwinnipeg.ca
Deep learning has become one of the most efficient computer vision tools in recent years.
The success and variety of deep learning semantic segmentation models inspired scientists …