发表机构
Nanyang Technological University; Zhejiang University; Beihang University; Beijing Institute of Technology; Yanshan University; Westlake University; University of Hong Kong; University of California, Los Angeles（南洋理工大学; 浙江大学; 北京航空航天大学; 北京理工大学; 燕山大学; 西湖大学; 香港大学; 加利福尼亚大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文构建了首个基础设施占用基准InfraOcc，提出ProSD-Occ方法实现静态-动态渐进推理，在多赛道排名第一，为固定视角路边占用提供了新的推理范式。
AI 中文摘要
固定视角的基础设施传感器会反复观测同一交通空间，使得路边3D占用感知与自车感知存在结构性差异：近乎持续存在的静态骨架上叠加着稀疏、短时长的动态事件。然而，现有的占用基准测试集与方法均围绕移动自车构建，既未衡量也未利用该结构，反而将占用视为扁平的单次体素分类。我们从数据与模型两方面解决这一缺口。我们构建了InfraOcc，据我们所知，这是首个真实世界的路边基础设施语义占用基准测试集，包含固定路边坐标系下290个多模态序列的密集体素标注、静态-动态解耦标注流水线、统一的仅相机、仅激光雷达及多模态评估，以及静态与动态占用的诊断。InfraOcc显示，静态基础设施占据97.3%的已占用体素且跨帧持续存在，而动态参与者在每个位置的中位已占用帧比例仅为1.8%，揭示出超出语义长尾分布的静态-动态结构性不对称性。我们进一步提出ProSD-Occ，其将占用重新表述为渐进式静态-动态证据推理：它解释持续布局、在静态置信度引导下暴露残差动态证据，并将静态、动态与自由空间证据重新组合为统一场。ProSD-Occ在所有赛道的整体、动态、静态及几何占用排名第一，例如，相比最强基线，仅相机动态mIoU提升23.5%，多模态整体mIoU为65.87，确立了固定视角路边占用为具有自身推理范式的独特问题。该基准测试集与代码将在this https URL公开提供。
英文摘要
Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle perception: a near-persistent static scaffold is overlaid with sparse, short-lived dynamic events. Existing occupancy benchmarks and methods, however, are built around moving ego vehicles and neither measure nor exploit this structure, instead treating occupancy as flat one-shot voxel classification. We address this gap from both data and model perspectives. We build InfraOcc, to our knowledge, the first real-world infrastructure-side semantic occupancy benchmark, with dense voxel annotations for 290 multi-modal sequences in a fixed roadside frame, a static-dynamic decoupled annotation pipeline, unified camera-only, LiDAR-only, and multi-modal evaluation, and diagnostics for static and dynamic occupancy. InfraOcc shows that static infrastructure fills 97.3% of occupied voxels and persists across frames, whereas dynamic participants have a median occupied-frame ratio of only 1.8% per location, revealing a structural static-dynamic asymmetry beyond semantic long-tailedness. We further propose ProSD-Occ, which reformulates occupancy as progressive static-to-dynamic evidence reasoning: it explains persistent layout, exposes residual dynamic evidence under static-confidence guidance, and recomposes static, dynamic, and free-space evidence into a unified field. ProSD-Occ ranks first in overall, dynamic, static, and geometric occupancy on every track, e.g., a 23.5% relative camera-only dynamic-mIoU gain over the strongest baseline and 65.87 multi-modal overall mIoU, establishing fixed-viewpoint roadside occupancy as a distinct problem with its own reasoning paradigm. The benchmark and code will be publicly available at https://github.com/yanglei18/InfraOcc
Comments17 pages, 12 figures
