mlsanityData to 7 Oct 2026

Out-of-Distribution Semantic Occupancy Prediction

arXiv 2506.21185 ↗First posted 26 Jun 2025cs.CV cs.RO eess.IVcited by 2

Not on the map. Why?

Abstract (arXiv)

3D semantic occupancy prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distribution scenes, making them susceptible to Out-of-Distribution (OoD) objects and long-tail distributions, which increase the risk of undetected anomalies and misinterpretations, posing safety hazards. To address these challenges, we introduce the task of Out-of-Distribution Semantic Occupancy Prediction, targeting OoD detection in 3D voxel space. To fill dataset gaps, we propose Realistic Anomaly Augmentation that injects synthetic anomalies while preserving realistic spatial and occlusion patterns, enabling the creation of two datasets: VAA-KITTI and VAA-KITTI-360. We then propose OccOoD, a novel framework that integrates OoD detection into 3D semantic occupancy prediction, which uses Cross-Space Semantic Refinement (CSSR) to refine semantic predictions from complementary voxel and BEV representations, improving OoD detection. Experimental results demonstrate that OccOoD achieves an AuROC of 65.50% and an AuPRCr of 31.83% within a 1.2m radius, while maintaining competitive semantic occupancy prediction accuracy, significantly improving detection sensitivity for unknown obstacles, and validating strong generalization in real-world urban driving scenes. The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 104 of its 123 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

104 of 123 references.

References · 104

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2024Depth Anything V2cited by 1,385
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  4. 2022Planning-oriented Autonomous Drivingcited by 1,068
  5. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  6. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  7. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  8. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  9. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  10. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  11. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  12. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
38 more
  1. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  2. 2023Scene as Occupancycited by 208
  3. 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
  4. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  5. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
  6. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  7. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  8. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  9. 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
  10. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  11. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 126
  12. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  13. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  14. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  15. 2024Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architecturescited by 97
  16. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  17. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  18. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 94
  19. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  20. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 88
  21. 2023NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Spacecited by 88
  22. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  23. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  24. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  25. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  26. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  27. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  28. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  29. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  30. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  31. 2022Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptorscited by 66
  32. 2023Fully Sparse 3D Occupancy Predictioncited by 61
  33. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  34. 2022Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentationcited by 55
  35. 2024POP-3D: Open-Vocabulary 3D Occupancy Prediction from Imagescited by 52
  36. 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
  37. 2024FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective Viewcited by 51
  38. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50

50 most cited of 104 All 104 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classescited by 0
  2. 2026ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Predictioncited by 0