mlsanityData to 14 Oct 2026

Can Image-To-Video Models Simulate Pedestrian Dynamics?

arXiv 2510.17731 ↗First posted 20 Oct 2025cs.CVcited by 1

On the map: World models → Video-generation world models and simulators

also in 1 more
Abstract (arXiv)

Recent high-performing image-to-video (I2V) models based on variants of the diffusion transformer (DiT) have displayed remarkable inherent world-modeling capabilities by virtue of training on large scale video datasets. We investigate whether these models can generate realistic pedestrian movement patterns in crowded public scenes. Our framework conditions I2V models on keyframes extracted from pedestrian trajectory benchmarks, then evaluates their trajectory prediction performance using quantitative measures of pedestrian dynamics.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Video-generation world models and simulators, one of 11 directions in World models. Builds on 20 of its 38 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

20 of 38 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness27 Mar
  2. 2025Wan: Open and Advanced Large-Scale Video Generative Models26 Mar
  3. 2024Open-Sora: Democratizing Efficient Video Production for All29 Dec
  4. 2024WorldSimBench: Towards Video Generation Models as World Simulators23 Oct
  5. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug

Other references · 15

  1. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  2. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  4. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 579
  5. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  6. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  7. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  8. 2024PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generationcited by 191
  9. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  10. 2024PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generationcited by 174
  11. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  12. 2024MotionCraft: Physics-based Zero-Shot Video Generationcited by 48
3 more
  1. 2025FullDiT: Multi-Task Video Generative Foundation Model with Full Attentioncited by 47
  2. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  3. 2024Understanding complex crowd dynamics with generative neural simulatorscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025PEDRA: Evaluating the Realism of Pedestrian Dynamics in Video Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection
  2. 2024Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
  3. 2026Image-to-Video Diffusion: From Foundations to Open Frontiers
  4. 2025SceneAware: Scene-Constrained Pedestrian Trajectory Prediction with LLM-Guided Walkability
  5. 2025Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
  6. 2025Intention Enhanced Diffusion Model for Multimodal Pedestrian Trajectory Prediction
  7. 2025Diffusion^2: Dual Diffusion Model with Uncertainty-Aware Adaptive Noise for Momentary Trajectory Prediction
  8. 2024MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation