{"ID":2923520,"CreatedAt":"2026-06-02T04:05:25.881865328Z","UpdatedAt":"2026-06-04T13:12:39.622923895Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02510","arxiv_id":"2606.02510","title":"Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2606.02510","url_pdf":"https://arxiv.org/pdf/2606.02510v1","authors":"[\"Xiang Xu\",\"Alan Liang\",\"Youquan Liu\",\"Xian Sun\",\"Linfeng Li\",\"Lingdong Kong\",\"Ziwei Liu\",\"Qingshan Liu\"]","published":"2026-06-01T17:24:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[\"Diffusion Model\"]","has_code":false}