Research map / Video / Video generation
DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
Yang Zhou, Hao Shao, Letian Wang, Zhuofan Zong, Hongsheng Li, Steven L. Waslander
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add failure handling to the SLAM trajectory pipeline (ablation) | DrivingGen SLAM · SLAM trajectory reconstruction (20 nuPlan Vista videos) | success rate: 17 / 20 -> 20 / 20 | Improved |
| add failure handling to the SLAM trajectory pipeline (ablation) | DrivingGen SLAM · SLAM trajectory reconstruction (20 nuPlan Vista videos) | ADE: 15.18 -> 16.84 | Hurt |
| use driving-specific model Vista instead of closed-source Kling 2.1 | ego-conditioned video generation · DrivingGen Ego-Conditioned Track | ADE: 29.97 -> 19.70 | Improved |
| use driving-specific VaViM instead of Kling 2.1 | video generation · DrivingGen Open-Domain Track | FVD: 693.4 -> 1446.6 | Hurt |
| use ego-trajectory conditioning (ego track vs open-domain) on Wan2.2-I2V | Wan2.2-I2V · DrivingGen FVD | FVD: 609.0 -> 194.4 | Improved |
| use driving-specific VaViM instead of Kling 2.1 | video generation · DrivingGen Open-Domain Track | trajectory consistency: 0.5377 -> 0.0914 | Hurt |
| use general model Cosmos-Predict2 instead of Kling 2.1 | video generation · DrivingGen Open-Domain Track | FVD: 693.4 -> 524.1 | Improved |
Closest papers by meaning
- Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving (CVPR 2024 · similarity 0.91)
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation (CVPR 2025 · similarity 0.90)
- ReSim: Reliable World Simulation for Autonomous Driving (NeurIPS 2025 · similarity 0.90)
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.90)
- SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model (CVPR 2025 · similarity 0.90)
- Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
