mlsanityData to 14 Oct 2026

RoadOcc Learns When to Persist, Transport, or Refresh Memory for Roadside Occupancy Prediction

arXiv 2609.27677 ↗First posted 23 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Fixed roadside cameras repeatedly observe a stable scene overlaid by sparse moving traffic. Temporal memory can recover weak observations, but reusing moving evidence at stale locations can corrupt occupancy predictions. Motion compensation addresses displacement, while reliance on the resulting history remains a separate learning problem. We introduce RoadOcc, which learns soft routing among fixed-coordinate history (Persist), velocity-addressed history (Transport), and current evidence (Refresh). Motion state and class-consistent historical support supervise these source choices. Dynamic-aware cross-attention (DCA) updates candidate locations, multi-scale voxel velocity estimation (VVE) constructs transport addresses from multi-scale current--history correspondence, and velocity-guided dynamic sparse fusion (VDSF) combines routed evidence under fixed sparse-token budgets. On InfraOcc, RoadOcc reaches 65.29 mIoU and 32.37 dynamic mIoU, gains of 4.44 and 4.71 over STCOcc. Controlled address experiments show that VVE raises dynamic mIoU by 0.87 over fixed-coordinate reading. Across three seeds, supervised P/T/R adds 1.40 dynamic points over motion-corrected retrieval, while removing Refresh costs 0.32 points. Results from two transfer models, Occ3D-nuScenes, and longer intervals provide additional support. Code will be released.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 23 Sep 2026.

Builds on

29 of 35 references.

References · 29

  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  2. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  3. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  4. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  5. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  6. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  7. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  8. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  9. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  10. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 233
  11. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  12. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
17 more
  1. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 157
  2. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  3. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  4. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 96
  5. 2023Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applicationscited by 52
  6. 2025UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Drivingcited by 28
  7. 2024OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Drivingcited by 27
  8. 2024Let Occ Flow: Self-Supervised 3D Occupancy Flow Predictioncited by 24
  9. 2025STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Predictioncited by 23
  10. 2024ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictionscited by 20
  11. 2025Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Predictioncited by 9
  12. 2025Occupancy Learning with Spatiotemporal Memorycited by 9
  13. 2024OFMPNet: Deep End-to-End Model for Occupancy and Flow Prediction in Urban Environmentcited by 8
  14. 2026ForecastOcc: Vision-based Semantic Occupancy Forecastingcited by 7
  15. 2025MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoringcited by 2
  16. 2026AsyncBEV: Cross-modal Flow Alignment in Asynchronous 3D Object Detectioncited by 2
  17. 2026InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoningcited by 2

Built on by

Not cited yet.