U4D通过感知不确定性，分阶段重建动态3D环境，提升生成质量与稳定性。
U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences
- 先定位语义复杂区域，再分两阶段逐步生成：高不确定性区优先精细重建
- 生成结果在几何精度和时间一致性上均优于现有方法，显著减少伪影
- 适合自动驾驶与具身AI的高可靠性4D世界建模需求
从激光雷达序列构建动态3D环境是实现自动驾驶与具身智能可靠4D世界的核心。现有生成框架通常对所有空间区域一视同仁，忽视真实场景中不确定性分布的差异，导致复杂或模糊区域出现伪影，影响真实感与时序稳定性。本文提出U4D，一种面向4D激光雷达世界建模的不确定性感知框架。首先利用预训练分割模型估计空间不确定性图，定位语义挑战区域；随后采用“由难到易”策略分两阶段生成：(1) 不确定性区域建模，对高熵区域进行高保真几何重建；(2) 不确定性条件补全，在学习到的结构先验下合成剩余区域。为增强时序一致性，U4D引入可自适应融合时空表示的时空混合（MoST）模块。大量实验表明，U4D生成的激光雷达序列在几何真实性与时序一致性上均显著提升，推动了自主感知与仿真中4D世界建模的可靠性。
原文摘要 · Abstract (English)
Modeling dynamic 3D environments from LiDAR sequences is central to building reliable 4D worlds for autonomous driving and embodied AI. Existing generative frameworks, however, often treat all spatial regions uniformly, overlooking the varying uncertainty across real-world scenes. This uniform generation leads to artifacts in complex or ambiguous regions, limiting realism and temporal stability. In this work, we present U4D, an uncertainty-aware framework for 4D LiDAR world modeling. Our approach first estimates spatial uncertainty maps from a pretrained segmentation model to localize semantically challenging regions. It then performs generation in a "hard-to-easy" manner through two sequential stages: (1) uncertainty-region modeling, which reconstructs high-entropy regions with fine geometric fidelity, and (2) uncertainty-conditioned completion, which synthesizes the remaining areas under learned structural priors. To further ensure temporal coherence, U4D incorporates a mixture of spatio-temporal (MoST) block that adaptively fuses spatial and temporal representations during diffusion. Extensive experiments show that U4D produces geometrically faithful and temporally consistent LiDAR sequences, advancing the reliability of 4D world modeling for autonomous perception and simulation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。