Research map / Video / Video generation
DrivingDiffusion: Layout-Guided Multi-View Driving Scenarios Video Generation with Latent Diffusion Model
Li Xiaofan, Zhang Yifu, Ye Xiaoqing
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 the consistency module (ablation) | DrivingDiffusion · nuScenes val | FVD: 420 -> 365 | Improved |
| add the local prompt (ablation) | DrivingDiffusion · nuScenes val | Object NDS: 28.1 -> 32.6 | Improved |
| add the local prompt alone (without consistency module) (ablation) | DrivingDiffusion · nuScenes val | FID: 17.30 -> 17.62 | Hurt |
| combine consistency module and local prompt (ablation) | DrivingDiffusion · nuScenes val | FID: 17.30 -> 15.83 | Improved |
| add 6,000 synthetic frames to BEVFusion training | BEVFusion · nuScenes val | Object NDS: 0.412 -> 0.434 | Improved |
| add 2,000 synthetic frames focused on orientation angles | BEVFusion · nuScenes val | Object NDS: 0.412 -> 0.418 | Improved |
| use DrivingDiffusion instead of BEVGen for layout-consistent generation | multi-view generation · nuScenes val (CVT) | Vehicle mIoU: 5.9 -> 31.6 | Improved |
Later papers that compared with this method
5 later accepted papers report DrivingDiffusion as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space (CVPR 2026 · better on 2 of 2 shared results)
- DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion (CVPR 2025 · better on 2 of 3 shared results)
- DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation (AAAI 2025 · better on 2 of 2 shared results)
- InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation (ICCV 2025 · better on 2 of 2 shared results)
- Generalized Predictive Model for Autonomous Driving (CVPR 2024 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DriveDreamer — DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion (CVPR 2025 · similarity 0.91)
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability (NeurIPS 2025 · similarity 0.89)
- DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation (AAAI 2025 · similarity 0.88)
- Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving (CVPR 2024 · similarity 0.88)
- UniScene: Unified Occupancy-centric Driving Scene Generation (CVPR 2025 · similarity 0.87)
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation (CVPR 2025 · similarity 0.87)
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.
