提出首个路侧静态-动态分离的3D占用基准与推理方法，解决固定视角感知难题
InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning
- 构建路侧视角的静态-动态解耦标注数据集，支持多模态评估
- 发现静态结构占97.3%体积且持久，动态目标仅1.8%帧占比，揭示结构性差异
- 新模型ProSD-Occ实现动态检测23.5%相对提升，适用于智能交通系统研发
固定视角的路侧传感器持续观测同一交通空间，使路侧3D占用结构不同于车载感知：存在近持久的静态骨架叠加稀疏短暂的动态事件。现有占用基准与方法基于移动车辆设计，既不测量也不利用此结构，将占用视为一次性体素分类。本文从数据与模型双角度填补该空白，构建InfraOcc——据知首个真实世界路侧语义占用基准，包含290组多模态序列的密集体素标注，采用静态-动态解耦标注流程，支持相机、激光雷达及多模态统一评估，并提供静态与动态占用诊断。InfraOcc显示静态基础设施占据97.3%的占用体素且跨帧持续，动态参与者每位置中位占用帧比仅为1.8%，揭示了超越语义长尾性的结构性静态-动态不对称。进一步提出ProSD-Occ，将占用建模为渐进式静态到动态证据推理：解释持久布局，于静态置信引导下暴露残余动态证据，并重组静态、动态与自由空间证据为统一场。ProSD-Occ在所有轨迹上整体、动态、静态及几何占用指标均排名第一，例如相机单模态动态mIoU较最强基线提升23.5%，多模态整体mIoU达65.87，确立固定视角路侧占用为具有独立推理范式的全新问题。基准与代码将公开于https://github.com/yanglei18/InfraOcc。
原文摘要 · Abstract (English)
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
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。