# Generating Driving Scenes with Diffusion

Source: [Generating Driving Scenes with Diffusion](<https://www.sota2.com/research/paper/68fa6f941e209131cea46637>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:23:24.960Z

Authors: Ethan Pronovost, Kai Wang, Nick Roy

Published: 2023-05-29T04:03:46.000Z

## Abstract

In this paper we describe a learned method of traffic scene generation designed to simulate the output of the perception system of a self-driving car. In our "Scene Diffusion" system, inspired by latent diffusion, we use a novel combination of diffusion and object detection to directly create realistic and physically plausible arrangements of discrete bounding boxes for agents. We show that our scene generation model is able to adapt to different regions in the US, producing scenarios that capture the intricacies of each region.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.18452>)

[PDF](<https://arxiv.org/pdf/2305.18452.pdf>)
