Automated creation of synthetic traffic scenarios is a key part of scaling the safety validation
of autonomous vehicles (AVs). In this paper, we propose Scenario Diffusion, a novel diffusion…

Addressing Lidar Panoptic Segmentation (LPS) is crucial for safe deployment of autnomous
vehicles. LPS aims to recognize and segment lidar points wrt a pre-defined vocabulary of …

… We thank Gary Linscott, Jake Ware, and Meghana Reddy Ganesina for helpful feedback on
the paper; Allan Zelener and Chris Song for discussions on object detection; Peter Schleede …

Traffic simulation aims to learn a policy for traffic agents that, when unrolled in closed-loop,
faithfully recovers the joint distribution of trajectories observed in the real world. Inspired by …

Diffusion models are emerging models that generate images by iteratively denoising
random Gaussian noise using deep neural networks. These models typically exhibit high …

We consider the task of traffic scene generation. A common approach in the self-driving industry
is to use manual creation to generate scenes with specific characteristics and automatic …

Simulation is of crucial importance for development and testing of autonomous vehicles. To
minimize the sim-toreal gap, the simulator should generate realistic scenarios. And to meet …

Diffusion models are emerging models that generate images by iteratively denoising
random Gaussian noise using deep neural networks. These models typically exhibit high …

Realistic and interactive scene simulation is a key prerequisite for autonomous vehicle (AV)
development. In this work, we present SceneDiffuser, a scene-level diffusion prior designed …

Simulation is critical for safety evaluation in autonomous driving, particularly in capturing
complex interactive behaviors. However, generating realistic and controllable traffic scenarios …