InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors note that sensors fixed on the roadside see mostly static objects with occasional moving ones, unlike sensors on moving cars. To study this, they created InfraOcc, a new dataset that labels 3D space from fixed viewpoints and separates static and dynamic objects. They also developed ProSD-Occ, a new model that first understands the static scene then identifies moving objects more effectively. Their method outperforms previous ones and highlights that fixed-location perception needs different approaches than car-mounted sensors.
3D occupancyinfrastructure sensorsstatic-dynamic occupancyvoxel classificationLiDARsemantic occupancymulti-modal sensor fusioncamera-only perceptionbenchmark datasetdynamic static decoupling
Authors
Lei Yang, Xiaokai Bai, Boqi Li, Chunmian Lin, Li Wang, Ziying Song, Jiahuan Zhang, Enhui Ma, Haibao Yu, Jiaqi Ma, Kaicheng Yu
Abstract
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