AI Paper Atlas

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

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 10 citations (OpenAlex)

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 changedWhereMeasuredEffect
increase range-map repeat height from 1 to 4 (ablation)LiDAR VAE · nuScenes LiDAR reconstructionChamfer Distance: 0.513 -> 0.154Improved
increase range-map repeat height from 1 to 4 (ablation)LiDAR VAE · nuScenes LiDAR reconstructionF-Score: 0.794 -> 0.900Improved
increase range-map repeat height from 2 to 4 (ablation)LiDAR VAE · nuScenes LiDAR reconstructionChamfer Distance: 0.336 -> 0.154Improved
add Unified Latent Anchoring (ULA) (ablation)UniDriveDreamer · nuScenes valcross-modal consistency (qualitative)Improved
replace OmniGen LiDAR VAE with the proposed LiDAR VAELiDAR reconstruction · nuScenes LiDAR reconstructionChamfer Distance: 0.793 -> 0.154Improved
replace OmniGen LiDAR VAE with the proposed LiDAR VAELiDAR reconstruction · nuScenes LiDAR reconstructionF-Score: 0.742 -> 0.900Improved
single-stage joint generation vs UniSceneLiDAR generation · nuScenes valMMD: 1.53 -> 0.27Improved
single-stage joint generation vs UniSceneLiDAR generation · nuScenes valJSD: 0.072 -> 0.039Improved
single-stage joint generation vs Genesiscamera generation · nuScenes valFID: 4.24 -> 2.81Improved
augment real training data with generated dataBEVFusion · nuScenes valmAP: 66.38 -> 67.18Improved
augment real training data with generated dataBEVFusion · nuScenes valNDS: 70.01 -> 70.53Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy