Research map / Vision-language and multimodal / Cross-modal learning
UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
Guosheng Zhao, Yaozeng Wang, Xiaofeng Wang, Zheng Zhu, Tingdong Yu, Guan Huang, Yongchen Zai, Ji Jiao, Changliang Xue, Xiaole Wang, Zhen Yang, Futang Zhu and 1 more
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 |
|---|---|---|---|
| increase range-map repeat height from 1 to 4 (ablation) | LiDAR VAE · nuScenes LiDAR reconstruction | Chamfer Distance: 0.513 -> 0.154 | Improved |
| increase range-map repeat height from 1 to 4 (ablation) | LiDAR VAE · nuScenes LiDAR reconstruction | F-Score: 0.794 -> 0.900 | Improved |
| increase range-map repeat height from 2 to 4 (ablation) | LiDAR VAE · nuScenes LiDAR reconstruction | Chamfer Distance: 0.336 -> 0.154 | Improved |
| add Unified Latent Anchoring (ULA) (ablation) | UniDriveDreamer · nuScenes val | cross-modal consistency (qualitative) | Improved |
| replace OmniGen LiDAR VAE with the proposed LiDAR VAE | LiDAR reconstruction · nuScenes LiDAR reconstruction | Chamfer Distance: 0.793 -> 0.154 | Improved |
| replace OmniGen LiDAR VAE with the proposed LiDAR VAE | LiDAR reconstruction · nuScenes LiDAR reconstruction | F-Score: 0.742 -> 0.900 | Improved |
| single-stage joint generation vs UniScene | LiDAR generation · nuScenes val | MMD: 1.53 -> 0.27 | Improved |
| single-stage joint generation vs UniScene | LiDAR generation · nuScenes val | JSD: 0.072 -> 0.039 | Improved |
| single-stage joint generation vs Genesis | camera generation · nuScenes val | FID: 4.24 -> 2.81 | Improved |
| augment real training data with generated data | BEVFusion · nuScenes val | mAP: 66.38 -> 67.18 | Improved |
| augment real training data with generated data | BEVFusion · nuScenes val | NDS: 70.01 -> 70.53 | Improved |
Closest papers by meaning
- Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency (NeurIPS 2025 · similarity 0.89)
- X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios (ICLR 2025 · similarity 0.88)
- Generating Multimodal Driving Scenes via Next-Scene Prediction (CVPR 2025 · similarity 0.87)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · similarity 0.87)
- Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis (NeurIPS 2026 · similarity 0.87)
- SceneCrafter: Controllable Multi-View Driving Scene Editing (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.
