Research map / Video / Video segmentation and tracking
Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space
Jian Zhu, Zhengyu Jia, Tian Gao, Jiaxin Deng, Shidi Li, Lang Zhang, Fu Liu, Peng Jia, Xianpeng Lang
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 other vehicle trajectories as condition (ablation) | EOT-WM · nuScenes val | FID: 7.2 -> 4.8 | Improved |
| add other vehicle trajectories as condition (ablation) | EOT-WM · nuScenes val | FVD: 66.1 -> 40.0 | Improved |
| add ego vehicle trajectory as condition (ablation) | EOT-WM · nuScenes val | FID: 49.6 -> 4.8 | Improved |
| add video-based trajectory representation (project trajectories into image space) (ablation) | EOT-WM · nuScenes val | FID: 55.3 -> 4.8 | Improved |
| encode trajectory video with the shared STVAE instead of C3D (AMGG) (ablation) | EOT-WM · nuScenes val | FID: 26.1 -> 4.8 | Improved |
| add text conditioning (scene description) to trajectory-conditioned model (ablation) | EOT-WM · nuScenes val | FID: 18.5 -> 4.8 | Improved |
| use action description text instead of scene description (ablation) | EOT-WM · nuScenes val | FID: 4.8 -> 4.1 | Improved |
| use instruction text instead of scene description (ablation) | EOT-WM · nuScenes val | FID: 4.8 -> 5.2 | No clear effect |
| use EOT-WM (ego and other trajectories in video space) instead of Vista | driving world model · nuScenes val | FID: 6.9 -> 4.8 | Improved |
| use EOT-WM instead of Vista | driving world model · nuScenes val | FVD: 89.4 -> 40.0 | Improved |
Closest papers by meaning
- Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability (NeurIPS 2024 · similarity 0.88)
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation (CVPR 2025 · similarity 0.87)
- Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving (CVPR 2024 · similarity 0.86)
- DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation (AAAI 2025 · similarity 0.86)
- Enhancing End-to-End Autonomous Driving with Latent World Model (ICLR 2025 · similarity 0.86)
- Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI 2025 · similarity 0.86)
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.
