mlsanityData to 7 Oct 2026

Generating Driving Scenes with Diffusion

arXiv 2305.18452 ↗First posted 29 May 2023cs.CV cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 25 of its 31 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

25 of 31 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  9. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  10. 2017Decoupled Weight Decay Regularizationcited by 1,722
  11. 2016Pixel Recurrent Neural Networkscited by 814
  12. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
13 more
  1. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  2. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 193
  3. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  4. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  5. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  6. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  7. 2019Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactionscited by 117
  8. 2022TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarioscited by 104
  9. 2021SceneGen: Learning to Generate Realistic Traffic Scenescited by 83
  10. 2021SimNet: Learning Reactive Self-driving Simulations from Real-world Observationscited by 77
  11. 2020What Makes for End-to-End Object Detection?cited by 47
  12. 2019Oriented Objects as pairs of Middle Linescited by 43
  13. 2021Oriented Bounding Boxes for Small and Freely Rotated Objectscited by 8

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 5; 2025: 6.

16 papers.

Sort:

By area:

  1. 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rolloutcited by 47
  2. 2025Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysiscited by 37
  3. 2023Data-driven Traffic Simulation: A Comprehensive Reviewcited by 29
  4. 2023SceneDM: Scene-level Multi-agent Trajectory Generation with Consistent Diffusion Modelscited by 24
  5. 2025SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Modelcited by 20
  6. 2023Applications of Large Scale Foundation Models for Autonomous Drivingcited by 14
  7. 2024Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Surveycited by 14
  8. 2024Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Modelscited by 13
  9. 2024UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarioscited by 10
  10. 2023Prospective Role of Foundation Models in Advancing Autonomous Vehiclescited by 7
  11. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  12. 2025Generative AI for Autonomous Driving: A Reviewcited by 3
4 more
  1. 2024Data-driven Diffusion Models for Enhancing Safety in Autonomous Vehicle Traffic Simulationscited by 2
  2. 2025Direct Preference Optimization-Enhanced Multi-Guided Diffusion Model for Traffic Scenario Generationcited by 2
  3. 2025Causal-Entity Reflected Egocentric Traffic Accident Video Synthesiscited by 2
  4. 2023TSDiT: Traffic Scene Diffusion Models With Transformerscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
  2. 2025EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial Representations
  3. 2025Optimization-Guided Diffusion for Interactive Scene Generation
  4. 2024DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving
  5. 2023Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
  6. 2025MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer
  7. 2024DreamDrive: Generative 4D Scene Modeling from Street View Images
  8. 2025Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving