AI Paper Atlas

Research map / 3D vision / 3D generation

U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

Xiang Xu, Alan Liang, Youquan Liu, Linfeng Li, Lingdong Kong, Ziwei Liu, Qingshan Liu

CVPR 2026 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 9 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
add entropy-based uncertainty region conditioning (ablation)U4D · nuScenes (uncertainty region ablation)FRD: 235.91 -> 223.96Improved
add random region conditioning instead of none (ablation)U4D · nuScenes (uncertainty region ablation)FRD: 235.91 -> 235.23No clear effect
use random region conditioning instead of none (ablation)U4D · nuScenes (uncertainty region ablation)ECE: 3.98 -> 4.35Hurt
add confidence-based region selection (ablation)U4D · nuScenes (uncertainty region ablation)FRD: 235.91 -> 228.24Improved
use entropy instead of confidence for region selection (ablation)U4D · nuScenes (uncertainty region ablation)ECE: 3.02 -> 2.72Improved
replace cascaded spatial-temporal with parallel addition fusion (ablation)MoST block · nuScenes (MoST ablation)FRD: 536.23 -> 242.81Improved
use concatenation instead of cascaded structure (ablation)MoST block · nuScenes (MoST ablation)FRD: 536.23 -> 242.43Improved
use adaptive fusion instead of concatenation (ablation)MoST block · nuScenes (MoST ablation)FRD: 242.43 -> 223.96Improved
use adaptive fusion instead of concatenation (ablation)MoST block · nuScenes (MoST ablation)FPD: 12.51 -> 12.90No clear effect
apply U4D generated data to semi-supervised segmentationMinkUNet · nuScenes semi-supervised segmentation (1% labels)mIoU: 58.3 -> 65.3Improved
apply U4D generated data to semi-supervised segmentationMinkUNet · nuScenes semi-supervised segmentation (50% labels)mIoU: 75.1 -> 76.4Improved
add U4D calibrationRangeNet++ · nuScenes val calibrationECE (%): 4.57 -> 2.72Improved

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