根据点云不确定性分层生成4D场景，提升复杂区域还原精度
Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis
- 按点云不确定性分层生成，难处优先精细重建
- 在nuScenes和SemanticKITTI上实现最佳场景保真度与时序一致性
- 适合需要高精度动态场景生成的自动驾驶研究者
从激光雷达序列构建真实4D世界对具身智能至关重要，但现有生成框架对所有空间区域采用统一建模能力，忽略了单次扫描内感知难度差异：远距离表面、被遮挡边界和小尺度物体的不确定性远高于可观测结构。本文提出U4D框架，通过预训练分割器计算各点的香农熵生成不确定性图，采用无条件扩散阶段优先合成高熵区域并保证几何精确性，再以这些结构为先验进行有条件补全。引入动态平衡空间细节与时间连续性的跨帧协同（MoST）模块。在nuScenes和SemanticKITTI上的实验表明，该方法在场景保真度、时序一致性及下游任务性能上均达当前最优水平。
原文摘要 · Abstract (English)
Constructing faithful 4D worlds from LiDAR-acquired sequences is crucial for embodied AI, yet current generative frameworks apply uniform modeling capacity across all spatial regions. This ignores that perceptual difficulty varies dramatically within a single scan: distant surfaces, occluded boundaries, and small-scale objects carry far higher uncertainty than well-observed structures. We present U4D, a new framework that explicitly leverages spatial uncertainty to guide LiDAR scene generation in a "hard-to-easy" schedule. U4D derives per-point uncertainty maps via Shannon Entropy from a pretrained segmentor, then applies an unconditional diffusion stage to synthesize high-entropy areas with precise geometry, followed by a conditional completion stage that fills in the remaining regions using these structures as priors. A MoST (Mixture of Spatio-Temporal) block further maintains cross-frame coherence by dynamically balancing spatial detail and temporal continuity. Extensive experiments on nuScenes and SemanticKITTI demonstrate state-of-the-art scene fidelity, temporal consistency, and downstream performance.
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。