mlsanityData to 14 Oct 2026

OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries

arXiv 2312.03774 ↗First posted 6 Dec 2023cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular grid representations, which often leads to excessive computational demands and a loss of spatial details for small objects. This paper introduces OctreeOcc, an innovative 3D occupancy prediction framework that leverages the octree representation to adaptively capture valuable information in 3D, offering variable granularity to accommodate object shapes and semantic regions of varying sizes and complexities. In particular, we incorporate image semantic information to improve the accuracy of initial octree structures and design an effective rectification mechanism to refine the octree structure iteratively. Our extensive evaluations show that OctreeOcc not only surpasses state-of-the-art methods in occupancy prediction, but also achieves a 15%-24% reduction in computational overhead compared to dense-grid-based methods.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 51 of its 59 references that are in the map. First posted on arXiv 6 Dec 2023.

Builds on

51 of 59 references.

References · 51

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2017Deformable Convolutional Networkscited by 1,488
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  9. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  11. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  12. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
38 more
  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  2. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  3. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  4. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  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. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  9. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  10. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  11. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  12. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  13. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 221
  14. 2023Scene as Occupancycited by 209
  15. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  16. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  17. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  18. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  19. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  20. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  21. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 128
  22. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 127
  23. 20203D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Priorcited by 126
  24. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  25. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  26. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 103
  27. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  28. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 96
  29. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 90
  30. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 90
  31. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  32. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 86
  33. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  34. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 61
  35. 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
  36. 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
  37. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  38. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 15; 2025: 20; 2026: 13.

48 papers.

Sort:

By area:

  1. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 157
  2. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 86
  3. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 67
  4. 2024RenderWorld: World Model with Self-Supervised 3D Labelcited by 46
  5. 2024A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspectivecited by 37
  6. 2024Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perceptioncited by 35
  7. 2024OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Predictioncited by 32
  8. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
  9. 2025GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flowcited by 24
  10. 2024GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervisioncited by 21
  11. 2024ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictionscited by 20
  12. 2025QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Predictioncited by 20
36 more
  1. 2025GaussRender: Learning 3D Occupancy with Gaussian Renderingcited by 18
  2. 2024LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Renderingcited by 16
  3. 2025GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attentioncited by 14
  4. 2024OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Predictioncited by 13
  5. 2024Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Drivingcited by 12
  6. 2026Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Predictioncited by 11
  7. 2025Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Predictioncited by 9
  8. 2025Semantic Causality-Aware Vision-Based 3D Occupancy Predictioncited by 8
  9. 2024ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learningcited by 6
  10. 2025ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimationcited by 6
  11. 2025Inverse++: Vision-Centric 3D Semantic Occupancy Prediction Assisted with 3D Object Detectioncited by 4
  12. 2025VG3T: Visual Geometry Grounded Gaussian Transformercited by 4
  13. 2024ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Cameracited by 3
  14. 2025SA-Occ: Satellite-Assisted 3D Occupancy Prediction in Real Worldcited by 3
  15. 2025GaussianFusionOcc: A Seamless Sensor Fusion Approach for 3D Occupancy Prediction Using 3D Gaussianscited by 3
  16. 2025Test-Time 3D Occupancy Predictioncited by 2
  17. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  18. 20264DRC-OCC: Robust Semantic Occupancy Prediction Through Fusion of 4D Radar and Cameracited by 2
  19. 2026FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Predictioncited by 2
  20. 2025Collaborative Learning of Local 3D Occupancy Prediction and Versatile Global Occupancy Mappingcited by 1
  21. 2025Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Constructioncited by 1
  22. 2025PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Taskscited by 1
  23. 2026FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Predictioncited by 1
  24. 2025OccLE: Label-Efficient 3D Semantic Occupancy Predictioncited by 0
  25. 2025DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Predictioncited by 0
  26. 2025From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Predictioncited by 0
  27. 2025Towards 3D Object-Centric Feature Learning for Semantic Scene Completioncited by 0
  28. 2026GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completioncited by 0
  29. 2026Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillationcited by 0
  30. 2026Semantic Occupancy Prediction with Dual Range-Voxel Representationcited by 0
  31. 2026GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perceptioncited by 0
  32. 2026SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Predictioncited by 0
  33. 2026GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priorscited by 0
  34. 2026InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecastingcited by 0
  35. 2026Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Drivingcited by 0
  36. 2026AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Taskscited by 0