{"ID":3004672,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T11:43:53.432517148Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03915","arxiv_id":"2606.03915","title":"PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion","abstract":"We propose PatchScene, a novel diffusion-based framework for large-scale LiDAR scene completion. Unlike existing methods that rely on global latent representations or dense voxel grids, PatchScene adopts a patch-based voxel diffusion paradigm that explicitly generates fine-grained geometry within localized 3D regions. To ensure coherent reconstruction at both spatial and temporal scales, we introduce a confidence-guided spatio-temporal fusion mechanism that integrates overlapping patches and adjacent frames in a unified generative process. Furthermore, we design an Annular-Flow diffusion strategy that leverages the radial density pattern of LiDAR scans to progressively propagate high-fidelity information from near-range to far-range regions, enabling spatially unbounded scene completion. Extensive experiments on the SemanticKITTI benchmark demonstrate that PatchScene achieves state-of-the-art performance across all standard metrics, surpassing previous approaches in both geometric accuracy and temporal consistency. Remarkably, the model trained on 20 m LiDAR ranges generalizes effectively to 50 m scenes without retraining, highlighting its strong scalability and generalization capability for real-world autonomous driving applications.","short_abstract":"We propose PatchScene, a novel diffusion-based framework for large-scale LiDAR scene completion. Unlike existing methods that rely on global latent representations or dense voxel grids, PatchScene adopts a patch-based voxel diffusion paradigm that explicitly generates fine-grained geometry within localized 3D regions....","url_abs":"https://arxiv.org/abs/2606.03915","url_pdf":"https://arxiv.org/pdf/2606.03915v1","authors":"[\"Qingdong Xu\",\"Jiajun Zhu\",\"Shilin Zhu\",\"Xinjing He\",\"Chao Lu\",\"Huanran Wang\",\"Jiyao Zhang\"]","published":"2026-06-02T17:09:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}